From 666c58384413f41e03c241fcf8fe9e100a8715c7 Mon Sep 17 00:00:00 2001 From: yy-fighting Date: Fri, 10 Jul 2026 02:20:36 +0000 Subject: [PATCH] vllm tp_dp_matrix: add final results (report, results.json, comparison, scenarios) Source code was already committed; this adds only the structured final artifacts from run 20260709-152419_matrix. Raw jsonl/logs/gpu_logs remain ignored per .gitignore. --- .../20260709-152419_matrix/comparison.md | 230 ++ .../skipped_after_oom.csv | 1 + .../20260709-152419_matrix/tp2_dp4/report.md | 70 + .../tp2_dp4/results.json | 3500 +++++++++++++++++ .../tp2_dp4/scenarios.tsv | 57 + .../20260709-152419_matrix/tp4_dp2/report.md | 70 + .../tp4_dp2/results.json | 3500 +++++++++++++++++ .../tp4_dp2/scenarios.tsv | 57 + .../20260709-152419_matrix/tp8_dp1/report.md | 70 + .../tp8_dp1/results.json | 3500 +++++++++++++++++ .../tp8_dp1/scenarios.tsv | 57 + 11 files changed, 11112 insertions(+) create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/comparison.md create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/skipped_after_oom.csv create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/report.md create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/results.json create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/scenarios.tsv create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/report.md create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/results.json create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/scenarios.tsv create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/report.md create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/results.json create mode 100644 experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/scenarios.tsv diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/comparison.md b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/comparison.md new file mode 100644 index 0000000..7922279 --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/comparison.md @@ -0,0 +1,230 @@ +# vLLM TP×DP matrix comparison (8x NVIDIA H200 143GB) + +## Summary + +- Model: `/data/models/DeepSeek-V4-Flash` +- Hardware: 8x NVIDIA H200 143GB +- Backend: vLLM +- Benchmark client: `sglang.bench_serving` +- SLO reference: TTFT P95 < 3000.0ms, TPOT mean < 50.0ms + +### Configurations + +| Config | TP | DP | GPUs/replica | Notes | +|---|---:|---:|---:|---| +| tp2_dp4 | 2 | 4 | 2 | server args recorded per ISL in results.json | +| tp4_dp2 | 4 | 2 | 4 | server args recorded per ISL in results.json | +| tp8_dp1 | 8 | 1 | 8 | server args recorded per ISL in results.json | + +## Side-by-side results + +| Scenario | ISL | DSL | Config | Conc | Req/s | OutTok/s | TTFT P95(ms) | TTFT P99(ms) | TPOT Mean(ms) | TPOT P95(ms) | TPOT P99(ms) | E2E P99(ms) | Peak GPU mem | SLO | +|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---| +| c1_i1024_o128 | 1024 | 128 | tp2_dp4 | 1 | 1.05 | 79.65 | 319.08 | 355.57 | 10.56 | 10.99 | 11.00 | 1406.84 | 138264/143771 (96.2%) | ✅ | +| c1_i1024_o128 | 1024 | 128 | tp4_dp2 | 1 | 1.34 | 101.85 | 302.85 | 345.83 | 8.17 | 8.32 | 8.35 | 1055.00 | 138396/143771 (96.3%) | ✅ | +| c1_i1024_o128 | 1024 | 128 | tp8_dp1 | 1 | 1.61 | 121.80 | 274.43 | 314.97 | 6.74 | 6.78 | 6.79 | 871.45 | 131900/143771 (91.7%) | ✅ | +| c1_i1024_o256 | 1024 | 256 | tp2_dp4 | 1 | 0.84 | 84.85 | 107.93 | 108.38 | 11.01 | 11.57 | 11.61 | 2082.56 | 139322/143771 (96.9%) | ✅ | +| c1_i1024_o256 | 1024 | 256 | tp4_dp2 | 1 | 1.12 | 113.80 | 88.52 | 90.59 | 8.12 | 8.21 | 8.23 | 1572.36 | 139454/143771 (97.0%) | ✅ | +| c1_i1024_o256 | 1024 | 256 | tp8_dp1 | 1 | 1.40 | 141.77 | 44.63 | 45.58 | 6.71 | 6.72 | 6.72 | 1281.54 | 132930/143771 (92.5%) | ✅ | +| c1_i1024_o512 | 1024 | 512 | tp2_dp4 | 1 | 0.79 | 79.92 | 113.71 | 115.02 | 11.50 | 11.85 | 11.86 | 2303.60 | 139322/143771 (96.9%) | ✅ | +| c1_i1024_o512 | 1024 | 512 | tp4_dp2 | 1 | 1.09 | 110.67 | 187.00 | 208.64 | 8.12 | 8.17 | 8.18 | 1572.17 | 139454/143771 (97.0%) | ✅ | +| c1_i1024_o512 | 1024 | 512 | tp8_dp1 | 1 | 1.36 | 137.55 | 65.04 | 65.69 | 6.74 | 6.78 | 6.79 | 1305.74 | 132930/143771 (92.5%) | ✅ | +| c1_i1024_o1024 | 1024 | 1024 | tp2_dp4 | 1 | 0.27 | 83.58 | 100.14 | 100.52 | 11.71 | 11.90 | 11.93 | 8200.76 | 139322/143771 (96.9%) | ✅ | +| c1_i1024_o1024 | 1024 | 1024 | tp4_dp2 | 1 | 0.39 | 120.49 | 90.47 | 90.97 | 8.11 | 8.19 | 8.21 | 5705.34 | 139456/143771 (97.0%) | ✅ | +| c1_i1024_o1024 | 1024 | 1024 | tp8_dp1 | 1 | 0.48 | 146.08 | 60.67 | 60.68 | 6.71 | 6.73 | 6.73 | 4727.62 | 132932/143771 (92.5%) | ✅ | +| c1_i1024_o2048 | 1024 | 2048 | tp2_dp4 | 1 | 0.08 | 84.74 | 105.11 | 105.45 | 11.70 | 11.81 | 11.81 | 20192.89 | 139322/143771 (96.9%) | ✅ | +| c1_i1024_o2048 | 1024 | 2048 | tp4_dp2 | 1 | 0.11 | 122.91 | 84.75 | 84.77 | 8.08 | 8.09 | 8.09 | 13978.61 | 139456/143771 (97.0%) | ✅ | +| c1_i1024_o2048 | 1024 | 2048 | tp8_dp1 | 1 | 0.13 | 148.32 | 60.19 | 62.81 | 6.71 | 6.72 | 6.72 | 11586.89 | 132932/143771 (92.5%) | ✅ | +| c1_i1024_o4096 | 1024 | 4096 | tp2_dp4 | 1 | 0.04 | 86.04 | 114.24 | 116.37 | 11.59 | 11.84 | 11.86 | 43455.08 | 139322/143771 (96.9%) | ✅ | +| c1_i1024_o4096 | 1024 | 4096 | tp4_dp2 | 1 | 0.05 | 122.97 | 82.10 | 82.14 | 8.09 | 8.12 | 8.13 | 30482.21 | 139456/143771 (97.0%) | ✅ | +| c1_i1024_o4096 | 1024 | 4096 | tp8_dp1 | 1 | 0.06 | 148.14 | 46.60 | 47.48 | 6.73 | 6.76 | 6.76 | 25332.98 | 132932/143771 (92.5%) | ✅ | +| c1_i4096_o128 | 4096 | 128 | tp2_dp4 | 1 | 0.92 | 69.56 | 353.45 | 371.20 | 11.63 | 11.95 | 12.00 | 1608.68 | 139322/143771 (96.9%) | ✅ | +| c1_i4096_o128 | 4096 | 128 | tp4_dp2 | 1 | 1.44 | 109.20 | 96.00 | 96.62 | 8.16 | 8.23 | 8.24 | 1054.23 | 139456/143771 (97.0%) | ✅ | +| c1_i4096_o128 | 4096 | 128 | tp8_dp1 | 1 | 1.62 | 122.84 | 148.51 | 155.20 | 6.72 | 6.74 | 6.74 | 918.13 | 132932/143771 (92.5%) | ✅ | +| c1_i4096_o256 | 4096 | 256 | tp2_dp4 | 1 | 0.77 | 78.01 | 208.90 | 226.63 | 11.61 | 11.87 | 11.89 | 2296.91 | 139324/143771 (96.9%) | ✅ | +| c1_i4096_o256 | 4096 | 256 | tp4_dp2 | 1 | 1.11 | 112.37 | 91.50 | 91.90 | 8.16 | 8.23 | 8.24 | 1604.71 | 139456/143771 (97.0%) | ✅ | +| c1_i4096_o256 | 4096 | 256 | tp8_dp1 | 1 | 1.37 | 138.57 | 67.18 | 67.54 | 6.73 | 6.77 | 6.78 | 1320.30 | 132932/143771 (92.5%) | ✅ | +| c1_i4096_o512 | 4096 | 512 | tp2_dp4 | 1 | 0.77 | 78.30 | 210.04 | 232.13 | 11.63 | 11.95 | 11.98 | 2378.47 | 139324/143771 (96.9%) | ✅ | +| c1_i4096_o512 | 4096 | 512 | tp4_dp2 | 1 | 1.10 | 111.43 | 104.51 | 107.11 | 8.16 | 8.24 | 8.25 | 1621.06 | 139456/143771 (97.0%) | ✅ | +| c1_i4096_o512 | 4096 | 512 | tp8_dp1 | 1 | 1.37 | 138.55 | 64.63 | 65.10 | 6.73 | 6.78 | 6.78 | 1320.67 | 132932/143771 (92.5%) | ✅ | +| c1_i4096_o1024 | 4096 | 1024 | tp2_dp4 | 1 | 0.27 | 83.60 | 113.91 | 115.64 | 11.55 | 11.86 | 11.87 | 8360.74 | 139324/143771 (96.9%) | ✅ | +| c1_i4096_o1024 | 4096 | 1024 | tp4_dp2 | 1 | 0.39 | 119.41 | 92.40 | 93.46 | 8.15 | 8.23 | 8.24 | 5771.30 | 139456/143771 (97.0%) | ✅ | +| c1_i4096_o1024 | 4096 | 1024 | tp8_dp1 | 1 | 0.47 | 144.76 | 66.58 | 66.81 | 6.73 | 6.78 | 6.79 | 4791.74 | 132932/143771 (92.5%) | ✅ | +| c1_i4096_o2048 | 4096 | 2048 | tp2_dp4 | 1 | 0.08 | 86.30 | 122.31 | 124.03 | 11.54 | 11.75 | 11.78 | 19528.19 | 139324/143771 (96.9%) | ✅ | +| c1_i4096_o2048 | 4096 | 2048 | tp4_dp2 | 1 | 0.11 | 121.84 | 105.61 | 108.34 | 8.13 | 8.16 | 8.16 | 14152.06 | 139824/143771 (97.3%) | ✅ | +| c1_i4096_o2048 | 4096 | 2048 | tp8_dp1 | 1 | 0.13 | 146.91 | 67.22 | 67.42 | 6.75 | 6.79 | 6.80 | 11755.04 | 132932/143771 (92.5%) | ✅ | +| c1_i4096_o4096 | 4096 | 4096 | tp2_dp4 | 1 | 0.04 | 85.60 | 130.43 | 132.68 | 11.66 | 11.87 | 11.89 | 43588.26 | 139324/143771 (96.9%) | ✅ | +| c1_i4096_o4096 | 4096 | 4096 | tp4_dp2 | 1 | 0.05 | 122.26 | 110.67 | 114.17 | 8.14 | 8.17 | 8.17 | 30710.72 | 139824/143771 (97.3%) | ✅ | +| c1_i4096_o4096 | 4096 | 4096 | tp8_dp1 | 1 | 0.06 | 147.18 | 66.70 | 66.85 | 6.77 | 6.80 | 6.80 | 25525.53 | 132932/143771 (92.5%) | ✅ | +| c1_i16384_o128 | 16384 | 128 | tp2_dp4 | 1 | 0.88 | 66.35 | 599.10 | 618.22 | 11.00 | 11.48 | 11.54 | 1948.72 | 139324/143771 (96.9%) | ✅ | +| c1_i16384_o128 | 16384 | 128 | tp4_dp2 | 1 | 1.14 | 86.24 | 512.76 | 518.98 | 8.11 | 8.23 | 8.25 | 1441.62 | 139824/143771 (97.3%) | ✅ | +| c1_i16384_o128 | 16384 | 128 | tp8_dp1 | 1 | 1.34 | 101.29 | 433.34 | 440.01 | 6.72 | 6.80 | 6.80 | 1242.36 | 132932/143771 (92.5%) | ✅ | +| c1_i16384_o256 | 16384 | 256 | tp2_dp4 | 1 | 0.71 | 71.69 | 448.96 | 486.54 | 11.52 | 11.66 | 11.67 | 2621.34 | 139324/143771 (96.9%) | ✅ | +| c1_i16384_o256 | 16384 | 256 | tp4_dp2 | 1 | 0.98 | 99.42 | 407.06 | 440.10 | 8.14 | 8.23 | 8.24 | 1937.46 | 139824/143771 (97.3%) | ✅ | +| c1_i16384_o256 | 16384 | 256 | tp8_dp1 | 1 | 1.31 | 132.55 | 122.35 | 122.83 | 6.73 | 6.76 | 6.76 | 1372.37 | 132932/143771 (92.5%) | ✅ | +| c1_i16384_o512 | 16384 | 512 | tp2_dp4 | 1 | 0.77 | 77.70 | 188.54 | 190.96 | 11.55 | 11.73 | 11.74 | 2356.50 | 139684/143771 (97.2%) | ✅ | +| c1_i16384_o512 | 16384 | 512 | tp4_dp2 | 1 | 1.07 | 108.69 | 155.92 | 157.11 | 8.16 | 8.23 | 8.25 | 1661.52 | 140338/143771 (97.6%) | ✅ | +| c1_i16384_o512 | 16384 | 512 | tp8_dp1 | 1 | 1.31 | 132.98 | 118.65 | 119.23 | 6.73 | 6.76 | 6.76 | 1365.21 | 132932/143771 (92.5%) | ✅ | +| c1_i16384_o1024 | 16384 | 1024 | tp2_dp4 | 1 | 0.27 | 83.88 | 322.92 | 349.35 | 11.31 | 11.64 | 11.64 | 7915.88 | 139684/143771 (97.2%) | ✅ | +| c1_i16384_o1024 | 16384 | 1024 | tp4_dp2 | 1 | 0.38 | 117.41 | 158.31 | 161.09 | 8.16 | 8.23 | 8.24 | 5837.98 | 140854/143771 (98.0%) | ✅ | +| c1_i16384_o1024 | 16384 | 1024 | tp8_dp1 | 1 | 0.46 | 141.13 | 132.08 | 134.06 | 6.75 | 6.80 | 6.81 | 4873.19 | 132932/143771 (92.5%) | ✅ | +| c1_i16384_o2048 | 16384 | 2048 | tp2_dp4 | 1 | 0.08 | 85.62 | 249.46 | 261.08 | 11.54 | 11.64 | 11.65 | 20210.50 | 139684/143771 (97.2%) | ✅ | +| c1_i16384_o2048 | 16384 | 2048 | tp4_dp2 | 1 | 0.11 | 121.16 | 155.57 | 156.44 | 8.14 | 8.18 | 8.19 | 14233.84 | 140854/143771 (98.0%) | ✅ | +| c1_i16384_o2048 | 16384 | 2048 | tp8_dp1 | 1 | 0.13 | 145.70 | 132.65 | 135.00 | 6.77 | 6.82 | 6.82 | 11867.20 | 132932/143771 (92.5%) | ✅ | +| c1_i65536_o128 | 65536 | 128 | tp2_dp4 | 1 | 0.44 | 33.25 | 2811.65 | 2892.88 | 11.47 | 12.08 | 12.21 | 4233.91 | 139706/143771 (97.2%) | ✅ | +| c1_i65536_o128 | 65536 | 128 | tp4_dp2 | 1 | 0.56 | 42.54 | 2211.56 | 2223.60 | 7.89 | 8.16 | 8.19 | 3092.42 | 140854/143771 (98.0%) | ✅ | +| c1_i65536_o128 | 65536 | 128 | tp8_dp1 | 1 | 0.84 | 63.38 | 1783.81 | 1903.90 | 6.67 | 6.75 | 6.75 | 2686.50 | 133260/143771 (92.7%) | ✅ | +| c1_i65536_o256 | 65536 | 256 | tp2_dp4 | 1 | 0.48 | 48.96 | 2181.49 | 2314.91 | 11.55 | 11.95 | 11.96 | 3709.96 | 139708/143771 (97.2%) | ✅ | +| c1_i65536_o256 | 65536 | 256 | tp4_dp2 | 1 | 1.01 | 102.18 | 274.65 | 283.52 | 7.97 | 8.23 | 8.25 | 1647.86 | 140854/143771 (98.0%) | ✅ | +| c1_i65536_o256 | 65536 | 256 | tp8_dp1 | 1 | 1.19 | 120.56 | 254.47 | 256.20 | 6.74 | 6.79 | 6.80 | 1352.80 | 133780/143771 (93.1%) | ✅ | +| c1_i65536_o512 | 65536 | 512 | tp2_dp4 | 1 | 0.62 | 63.19 | 1276.37 | 1453.96 | 11.06 | 11.68 | 11.78 | 2624.42 | 139708/143771 (97.2%) | ✅ | +| c1_i65536_o512 | 65536 | 512 | tp4_dp2 | 1 | 0.98 | 99.45 | 326.62 | 330.25 | 7.91 | 8.17 | 8.18 | 1655.09 | 140854/143771 (98.0%) | ✅ | +| c1_i65536_o512 | 65536 | 512 | tp8_dp1 | 1 | 1.18 | 119.95 | 288.97 | 290.20 | 6.54 | 6.74 | 6.75 | 1356.99 | 133780/143771 (93.1%) | ✅ | +| c1_i65536_o1024 | 65536 | 1024 | tp2_dp4 | 1 | 0.27 | 83.13 | 375.58 | 383.90 | 11.12 | 11.57 | 11.58 | 8213.89 | 139708/143771 (97.2%) | ✅ | +| c1_i65536_o1024 | 65536 | 1024 | tp4_dp2 | 1 | 0.37 | 112.31 | 358.50 | 364.11 | 8.07 | 8.26 | 8.26 | 5842.34 | 140854/143771 (98.0%) | ✅ | +| c1_i65536_o1024 | 65536 | 1024 | tp8_dp1 | 1 | 0.45 | 136.44 | 254.42 | 254.84 | 6.76 | 6.85 | 6.86 | 4841.93 | 133780/143771 (93.1%) | ✅ | +| c1_i131072_o128 | 131072 | 128 | tp2_dp4 | 1 | 0.32 | 24.40 | 3831.71 | 3847.18 | 11.06 | 11.65 | 11.68 | 5071.55 | 140228/143771 (97.5%) | ⚠️ | +| c1_i131072_o128 | 131072 | 128 | tp4_dp2 | 1 | 0.38 | 28.62 | 3498.43 | 3510.98 | 7.74 | 8.18 | 8.22 | 4353.06 | 141374/143771 (98.3%) | ⚠️ | +| c1_i131072_o128 | 131072 | 128 | tp8_dp1 | 1 | 0.55 | 42.03 | 3042.40 | 3072.01 | 6.34 | 6.70 | 6.72 | 3832.09 | 133780/143771 (93.1%) | ⚠️ | +| c1_i131072_o256 | 131072 | 256 | tp2_dp4 | 1 | 0.46 | 46.84 | 3143.30 | 3630.53 | 11.11 | 11.90 | 11.97 | 4950.01 | 140228/143771 (97.5%) | ⚠️ | +| c1_i131072_o256 | 131072 | 256 | tp4_dp2 | 1 | 0.61 | 61.94 | 2612.01 | 3033.01 | 7.81 | 8.23 | 8.24 | 3829.62 | 141374/143771 (98.3%) | ✅ | +| c1_i131072_o256 | 131072 | 256 | tp8_dp1 | 1 | 1.03 | 104.48 | 526.13 | 531.79 | 6.38 | 6.74 | 6.75 | 1365.14 | 134302/143771 (93.4%) | ✅ | +| c1_i131072_o512 | 131072 | 512 | tp2_dp4 | 1 | 0.67 | 68.11 | 574.50 | 577.45 | 10.89 | 11.54 | 11.54 | 2318.95 | 140228/143771 (97.5%) | ✅ | +| c1_i131072_o512 | 131072 | 512 | tp4_dp2 | 1 | 0.89 | 90.55 | 555.04 | 573.87 | 7.81 | 8.24 | 8.27 | 1649.69 | 141374/143771 (98.3%) | ✅ | +| c1_i131072_o512 | 131072 | 512 | tp8_dp1 | 1 | 1.03 | 104.09 | 528.58 | 529.52 | 6.38 | 6.74 | 6.75 | 1365.66 | 134302/143771 (93.4%) | ✅ | +| c1_i262144_o128 | 262144 | 128 | tp2_dp4 | 1 | 0.15 | 11.35 | 13444.27 | 14788.12 | 9.88 | 11.09 | 11.15 | 16032.30 | 140744/143771 (97.9%) | ⚠️ | +| c1_i262144_o128 | 262144 | 128 | tp4_dp2 | 1 | 0.20 | 15.35 | 8221.07 | 8613.48 | 6.70 | 7.64 | 7.66 | 9509.11 | 141374/143771 (98.3%) | ⚠️ | +| c1_i262144_o128 | 262144 | 128 | tp8_dp1 | 1 | 0.23 | 17.26 | 7547.16 | 7933.13 | 5.31 | 6.25 | 6.26 | 8667.71 | 134304/143771 (93.4%) | ⚠️ | +| c1_i262144_o256 | 262144 | 256 | tp2_dp4 | 1 | 0.18 | 18.19 | 8943.43 | 9385.72 | 10.07 | 11.43 | 11.50 | 10671.30 | 141258/143771 (98.3%) | ⚠️ | +| c1_i262144_o256 | 262144 | 256 | tp4_dp2 | 1 | 0.71 | 72.25 | 962.12 | 1036.06 | 6.92 | 7.88 | 7.93 | 2080.08 | 141374/143771 (98.3%) | ✅ | +| c1_i262144_o256 | 262144 | 256 | tp8_dp1 | 1 | 0.91 | 92.31 | 741.06 | 802.19 | 5.45 | 6.50 | 6.55 | 1664.47 | 134304/143771 (93.4%) | ✅ | +| c1_i524288_o128 | 524288 | 128 | tp2_dp4 | 1 | 0.13 | 9.76 | 17139.22 | 19091.80 | 9.70 | 10.39 | 10.40 | 20099.12 | 141258/143771 (98.3%) | ⚠️ | +| c1_i524288_o128 | 524288 | 128 | tp4_dp2 | 1 | 0.21 | 16.00 | 14806.51 | 17551.38 | 6.63 | 7.42 | 7.46 | 18281.61 | 141374/143771 (98.3%) | ⚠️ | +| c1_i524288_o128 | 524288 | 128 | tp8_dp1 | 1 | 0.23 | 17.65 | 13982.40 | 16622.77 | 5.18 | 6.10 | 6.17 | 17210.26 | 134304/143771 (93.4%) | ⚠️ | +| c1_i1048576_o128 | 1048576 | 128 | tp2_dp4 | 1 | 0.06 | 4.85 | 46081.66 | 51394.85 | 8.95 | 10.50 | 10.51 | 51849.45 | 141258/143771 (98.3%) | ⚠️ | +| c1_i1048576_o128 | 1048576 | 128 | tp4_dp2 | 1 | 0.06 | 4.88 | 43228.08 | 48170.56 | 6.14 | 7.51 | 7.56 | 48471.96 | 141374/143771 (98.3%) | ⚠️ | +| c1_i1048576_o128 | 1048576 | 128 | tp8_dp1 | 1 | 0.10 | 7.26 | 38265.96 | 45702.81 | 4.67 | 6.04 | 6.08 | 45912.47 | 134310/143771 (93.4%) | ⚠️ | +| c2_i262144_o128 | 262144 | 128 | tp2_dp4 | 2 | 0.27 | 20.65 | 9292.65 | 9433.23 | 24.30 | 74.40 | 75.57 | 10323.72 | 140744/143771 (97.9%) | ⚠️ | +| c2_i262144_o128 | 262144 | 128 | tp4_dp2 | 2 | 0.33 | 24.58 | 7994.94 | 8377.33 | 25.23 | 70.28 | 72.19 | 9106.67 | 141374/143771 (98.3%) | ⚠️ | +| c2_i262144_o128 | 262144 | 128 | tp8_dp1 | 2 | 0.58 | 43.70 | 6405.29 | 6864.92 | 12.04 | 40.84 | 63.02 | 7624.83 | 134304/143771 (93.4%) | ⚠️ | +| c2_i262144_o256 | 262144 | 256 | tp2_dp4 | 2 | 0.30 | 42.07 | 9153.02 | 10642.68 | 24.92 | 66.10 | 74.81 | 12104.02 | 141258/143771 (98.3%) | ⚠️ | +| c2_i262144_o256 | 262144 | 256 | tp4_dp2 | 2 | 0.48 | 66.52 | 6399.54 | 6424.61 | 10.75 | 22.96 | 32.38 | 8063.51 | 141374/143771 (98.3%) | ⚠️ | +| c2_i262144_o256 | 262144 | 256 | tp8_dp1 | 2 | 1.23 | 171.18 | 872.87 | 960.16 | 6.69 | 7.16 | 7.25 | 2191.39 | 134304/143771 (93.4%) | ✅ | +| c2_i524288_o128 | 524288 | 128 | tp2_dp4 | 2 | 0.69 | 52.24 | 4695.87 | 6463.46 | 15.77 | 44.14 | 65.40 | 8060.58 | 141258/143771 (98.3%) | ⚠️ | +| c2_i524288_o128 | 524288 | 128 | tp4_dp2 | 2 | 0.64 | 48.43 | 6241.67 | 9313.98 | 44.54 | 213.86 | 348.24 | 10806.98 | 141374/143771 (98.3%) | ⚠️ | +| c2_i524288_o128 | 524288 | 128 | tp8_dp1 | 2 | 1.76 | 133.35 | 1167.12 | 1232.75 | 5.64 | 6.90 | 6.94 | 1708.86 | 134306/143771 (93.4%) | ✅ | +| c2_i1048576_o128 | 1048576 | 128 | tp2_dp4 | 2 | 0.06 | 4.16 | 61414.70 | 65340.99 | 117.07 | 500.43 | 531.18 | 66294.91 | 141780/143771 (98.6%) | ❌ | +| c2_i1048576_o128 | 1048576 | 128 | tp4_dp2 | 2 | 0.06 | 4.56 | 51577.89 | 52987.83 | 277.94 | 766.41 | 858.05 | 56546.05 | 141374/143771 (98.3%) | ❌ | +| c2_i1048576_o128 | 1048576 | 128 | tp8_dp1 | 2 | 0.08 | 6.16 | 59936.57 | 60383.98 | 15.73 | 56.69 | 68.50 | 66073.78 | 134312/143771 (93.4%) | ⚠️ | +| c4_i131072_o128 | 131072 | 128 | tp2_dp4 | 4 | 0.74 | 41.97 | 5381.79 | 6485.26 | 63.46 | 234.23 | 254.36 | 9800.84 | 140228/143771 (97.5%) | ❌ | +| c4_i131072_o128 | 131072 | 128 | tp4_dp2 | 4 | 0.61 | 34.68 | 7688.92 | 7746.95 | 55.15 | 151.40 | 157.05 | 13546.32 | 141374/143771 (98.3%) | ❌ | +| c4_i131072_o128 | 131072 | 128 | tp8_dp1 | 4 | 0.82 | 46.76 | 5665.45 | 7563.45 | 46.92 | 130.55 | 135.39 | 9263.16 | 134302/143771 (93.4%) | ⚠️ | +| c4_i131072_o256 | 131072 | 256 | tp2_dp4 | 4 | 0.51 | 64.78 | 4431.12 | 6485.73 | 38.02 | 82.59 | 93.31 | 21326.10 | 140228/143771 (97.5%) | ⚠️ | +| c4_i131072_o256 | 131072 | 256 | tp4_dp2 | 4 | 0.79 | 101.20 | 6019.33 | 6092.09 | 20.62 | 43.90 | 46.90 | 10875.06 | 141374/143771 (98.3%) | ⚠️ | +| c4_i131072_o256 | 131072 | 256 | tp8_dp1 | 4 | 2.40 | 306.01 | 826.11 | 873.84 | 7.11 | 8.42 | 8.69 | 2602.99 | 134302/143771 (93.4%) | ✅ | +| c4_i131072_o512 | 131072 | 512 | tp2_dp4 | 4 | 0.46 | 136.39 | 5162.58 | 5751.13 | 24.26 | 43.94 | 51.73 | 14391.10 | 140228/143771 (97.5%) | ⚠️ | +| c4_i131072_o512 | 131072 | 512 | tp4_dp2 | 4 | 1.03 | 302.02 | 724.28 | 1360.67 | 9.94 | 13.97 | 16.16 | 5861.60 | 141374/143771 (98.3%) | ✅ | +| c4_i131072_o512 | 131072 | 512 | tp8_dp1 | 4 | 1.30 | 382.40 | 581.21 | 686.73 | 7.67 | 8.27 | 8.30 | 4365.16 | 134302/143771 (93.4%) | ✅ | +| c8_i65536_o128 | 65536 | 128 | tp2_dp4 | 8 | 0.86 | 55.23 | 5855.87 | 7061.54 | 115.39 | 327.74 | 399.92 | 18685.86 | 139708/143771 (97.2%) | ❌ | +| c8_i65536_o128 | 65536 | 128 | tp4_dp2 | 8 | 0.94 | 60.49 | 5620.08 | 5766.46 | 118.91 | 301.63 | 309.58 | 16549.56 | 140854/143771 (98.0%) | ❌ | +| c8_i65536_o128 | 65536 | 128 | tp8_dp1 | 8 | 1.01 | 64.77 | 7445.34 | 8645.53 | 88.42 | 248.75 | 263.80 | 16484.17 | 133780/143771 (93.1%) | ❌ | +| c8_i65536_o256 | 65536 | 256 | tp2_dp4 | 8 | 0.90 | 117.73 | 4029.43 | 4806.74 | 54.45 | 101.30 | 122.71 | 18052.15 | 139708/143771 (97.2%) | ❌ | +| c8_i65536_o256 | 65536 | 256 | tp4_dp2 | 8 | 1.31 | 171.79 | 3353.05 | 4860.71 | 44.63 | 113.59 | 141.58 | 15303.64 | 140854/143771 (98.0%) | ⚠️ | +| c8_i65536_o256 | 65536 | 256 | tp8_dp1 | 8 | 4.63 | 608.09 | 749.11 | 864.77 | 9.14 | 10.21 | 10.30 | 2998.37 | 133780/143771 (93.1%) | ✅ | +| c8_i65536_o512 | 65536 | 512 | tp2_dp4 | 8 | 0.98 | 272.84 | 3168.19 | 5671.91 | 24.56 | 51.52 | 85.56 | 18250.24 | 139708/143771 (97.2%) | ⚠️ | +| c8_i65536_o512 | 65536 | 512 | tp4_dp2 | 8 | 1.47 | 410.24 | 1809.22 | 2638.39 | 17.90 | 23.23 | 79.99 | 9676.38 | 140854/143771 (98.0%) | ✅ | +| c8_i65536_o512 | 65536 | 512 | tp8_dp1 | 8 | 2.53 | 705.69 | 661.39 | 679.12 | 9.10 | 9.63 | 10.39 | 5200.71 | 133780/143771 (93.1%) | ✅ | +| c8_i65536_o1024 | 65536 | 1024 | tp2_dp4 | 8 | 0.64 | 351.24 | 2850.09 | 2967.29 | 19.43 | 29.44 | 36.68 | 21507.37 | 139708/143771 (97.2%) | ✅ | +| c8_i65536_o1024 | 65536 | 1024 | tp4_dp2 | 8 | 0.97 | 528.38 | 2177.55 | 2783.15 | 13.13 | 20.42 | 32.65 | 13878.42 | 140854/143771 (98.0%) | ✅ | +| c8_i65536_o1024 | 65536 | 1024 | tp8_dp1 | 8 | 1.34 | 734.78 | 671.08 | 707.77 | 8.91 | 9.20 | 10.49 | 9476.99 | 133780/143771 (93.1%) | ✅ | +| c32_i16384_o128 | 16384 | 128 | tp2_dp4 | 32 | 4.31 | 284.72 | 3298.27 | 4051.80 | 107.21 | 186.59 | 376.91 | 15245.93 | 139324/143771 (96.9%) | ❌ | +| c32_i16384_o128 | 16384 | 128 | tp4_dp2 | 32 | 5.16 | 340.76 | 3479.51 | 3760.82 | 85.23 | 160.17 | 235.33 | 12999.09 | 139824/143771 (97.3%) | ❌ | +| c32_i16384_o128 | 16384 | 128 | tp8_dp1 | 32 | 5.39 | 356.17 | 3789.36 | 4532.55 | 78.86 | 150.73 | 226.61 | 11830.35 | 132932/143771 (92.5%) | ❌ | +| c32_i16384_o256 | 16384 | 256 | tp2_dp4 | 32 | 4.49 | 623.03 | 1913.91 | 2384.97 | 47.34 | 71.67 | 147.97 | 13936.33 | 139684/143771 (97.2%) | ✅ | +| c32_i16384_o256 | 16384 | 256 | tp4_dp2 | 32 | 5.41 | 751.48 | 1701.48 | 2572.97 | 38.88 | 55.35 | 126.86 | 11645.26 | 140338/143771 (97.6%) | ✅ | +| c32_i16384_o256 | 16384 | 256 | tp8_dp1 | 32 | 12.84 | 1782.54 | 636.48 | 644.96 | 14.84 | 16.94 | 20.78 | 4262.99 | 132932/143771 (92.5%) | ✅ | +| c32_i16384_o512 | 16384 | 512 | tp2_dp4 | 32 | 3.77 | 952.48 | 1520.07 | 2259.12 | 30.21 | 45.07 | 57.04 | 18769.12 | 139684/143771 (97.2%) | ✅ | +| c32_i16384_o512 | 16384 | 512 | tp4_dp2 | 32 | 5.44 | 1373.00 | 965.45 | 1010.01 | 20.31 | 25.61 | 28.12 | 12002.66 | 140854/143771 (98.0%) | ✅ | +| c32_i16384_o512 | 16384 | 512 | tp8_dp1 | 32 | 7.83 | 1977.19 | 640.86 | 739.06 | 14.04 | 15.70 | 18.53 | 7504.82 | 132932/143771 (92.5%) | ✅ | +| c32_i16384_o1024 | 16384 | 1024 | tp2_dp4 | 32 | 2.52 | 1337.54 | 1871.97 | 2404.37 | 22.95 | 27.86 | 72.28 | 22977.81 | 139684/143771 (97.2%) | ✅ | +| c32_i16384_o1024 | 16384 | 1024 | tp4_dp2 | 32 | 3.21 | 1704.78 | 1131.20 | 1660.57 | 17.14 | 21.79 | 37.19 | 18824.49 | 140854/143771 (98.0%) | ✅ | +| c32_i16384_o1024 | 16384 | 1024 | tp8_dp1 | 32 | 4.00 | 2122.35 | 789.94 | 950.40 | 13.38 | 14.23 | 22.02 | 13797.93 | 132932/143771 (92.5%) | ✅ | +| c32_i16384_o2048 | 16384 | 2048 | tp2_dp4 | 32 | 1.56 | 1785.47 | 1089.13 | 1111.26 | 15.83 | 17.47 | 19.70 | 33430.94 | 139684/143771 (97.2%) | ✅ | +| c32_i16384_o2048 | 16384 | 2048 | tp4_dp2 | 32 | 1.73 | 1982.72 | 1143.92 | 2172.49 | 14.60 | 16.68 | 25.49 | 30322.94 | 140854/143771 (98.0%) | ✅ | +| c32_i16384_o2048 | 16384 | 2048 | tp8_dp1 | 32 | 1.94 | 2226.25 | 628.02 | 806.24 | 12.88 | 13.39 | 14.85 | 26578.49 | 132932/143771 (92.5%) | ✅ | +| c64_i4096_o128 | 4096 | 128 | tp2_dp4 | 64 | 11.02 | 721.10 | 1790.01 | 2034.19 | 83.97 | 111.62 | 188.61 | 12237.14 | 139324/143771 (96.9%) | ⚠️ | +| c64_i4096_o128 | 4096 | 128 | tp4_dp2 | 64 | 10.43 | 682.69 | 1904.20 | 2262.19 | 88.50 | 123.52 | 173.68 | 12463.74 | 139456/143771 (97.0%) | ⚠️ | +| c64_i4096_o128 | 4096 | 128 | tp8_dp1 | 64 | 11.81 | 772.92 | 2978.27 | 3725.28 | 76.32 | 108.07 | 233.29 | 11989.51 | 132932/143771 (92.5%) | ⚠️ | +| c64_i4096_o256 | 4096 | 256 | tp2_dp4 | 64 | 8.50 | 1101.01 | 1290.52 | 1667.29 | 55.00 | 72.09 | 89.93 | 15631.13 | 139324/143771 (96.9%) | ⚠️ | +| c64_i4096_o256 | 4096 | 256 | tp4_dp2 | 64 | 10.23 | 1323.77 | 1198.05 | 1234.72 | 45.94 | 59.77 | 82.58 | 13085.09 | 139456/143771 (97.0%) | ✅ | +| c64_i4096_o256 | 4096 | 256 | tp8_dp1 | 64 | 19.45 | 2518.43 | 804.28 | 815.33 | 22.25 | 25.88 | 28.53 | 6644.63 | 132932/143771 (92.5%) | ✅ | +| c64_i4096_o512 | 4096 | 512 | tp2_dp4 | 64 | 6.47 | 1712.46 | 1099.58 | 1280.63 | 32.92 | 40.95 | 51.15 | 18838.52 | 139324/143771 (96.9%) | ✅ | +| c64_i4096_o512 | 4096 | 512 | tp4_dp2 | 64 | 8.10 | 2143.08 | 946.13 | 974.08 | 26.25 | 32.55 | 35.60 | 15173.06 | 139456/143771 (97.0%) | ✅ | +| c64_i4096_o512 | 4096 | 512 | tp8_dp1 | 64 | 11.71 | 3100.03 | 584.91 | 601.95 | 17.83 | 18.78 | 19.95 | 9668.74 | 132932/143771 (92.5%) | ✅ | +| c64_i4096_o1024 | 4096 | 1024 | tp2_dp4 | 64 | 4.39 | 2351.38 | 1083.22 | 1200.04 | 24.41 | 28.13 | 32.24 | 26088.66 | 139324/143771 (96.9%) | ✅ | +| c64_i4096_o1024 | 4096 | 1024 | tp4_dp2 | 64 | 5.45 | 2915.21 | 1023.51 | 1212.54 | 19.18 | 21.78 | 24.49 | 21920.34 | 139824/143771 (97.3%) | ✅ | +| c64_i4096_o1024 | 4096 | 1024 | tp8_dp1 | 64 | 6.14 | 3283.93 | 789.79 | 800.08 | 17.06 | 17.95 | 19.33 | 17906.82 | 132932/143771 (92.5%) | ✅ | +| c64_i4096_o2048 | 4096 | 2048 | tp2_dp4 | 64 | 2.73 | 2846.07 | 1149.71 | 1194.86 | 19.80 | 22.43 | 24.96 | 41227.42 | 139324/143771 (96.9%) | ✅ | +| c64_i4096_o2048 | 4096 | 2048 | tp4_dp2 | 64 | 3.04 | 3165.95 | 856.07 | 869.36 | 17.64 | 18.77 | 20.69 | 37188.62 | 139824/143771 (97.3%) | ✅ | +| c64_i4096_o2048 | 4096 | 2048 | tp8_dp1 | 64 | 3.28 | 3408.88 | 570.75 | 582.03 | 16.56 | 17.06 | 18.07 | 34336.54 | 132932/143771 (92.5%) | ✅ | +| c64_i4096_o4096 | 4096 | 4096 | tp2_dp4 | 64 | 1.49 | 3050.95 | 900.93 | 999.74 | 17.93 | 19.28 | 20.04 | 75036.72 | 139324/143771 (96.9%) | ✅ | +| c64_i4096_o4096 | 4096 | 4096 | tp4_dp2 | 64 | 1.62 | 3323.06 | 727.11 | 753.66 | 16.53 | 17.22 | 17.64 | 68039.71 | 139824/143771 (97.3%) | ✅ | +| c64_i4096_o4096 | 4096 | 4096 | tp8_dp1 | 64 | 1.67 | 3408.94 | 576.41 | 599.00 | 16.44 | 16.79 | 16.98 | 68183.67 | 132932/143771 (92.5%) | ✅ | +| c128_i1024_o128 | 1024 | 128 | tp2_dp4 | 128 | 14.09 | 919.53 | 1787.94 | 1815.68 | 131.99 | 159.76 | 191.60 | 19385.13 | 139322/143771 (96.9%) | ⚠️ | +| c128_i1024_o128 | 1024 | 128 | tp4_dp2 | 128 | 15.24 | 994.43 | 1659.18 | 1917.69 | 122.83 | 156.63 | 189.20 | 18386.47 | 139454/143771 (97.0%) | ⚠️ | +| c128_i1024_o128 | 1024 | 128 | tp8_dp1 | 128 | 25.21 | 1644.87 | 1647.93 | 2127.36 | 71.51 | 108.98 | 146.42 | 11987.25 | 132930/143771 (92.5%) | ⚠️ | +| c128_i1024_o256 | 1024 | 256 | tp2_dp4 | 128 | 12.51 | 1654.84 | 1302.99 | 1324.67 | 72.57 | 92.16 | 105.85 | 20487.34 | 139322/143771 (96.9%) | ⚠️ | +| c128_i1024_o256 | 1024 | 256 | tp4_dp2 | 128 | 15.10 | 1996.42 | 938.43 | 1171.74 | 60.05 | 74.97 | 96.47 | 16952.04 | 139454/143771 (97.0%) | ⚠️ | +| c128_i1024_o256 | 1024 | 256 | tp8_dp1 | 128 | 23.31 | 3082.56 | 725.46 | 741.75 | 37.61 | 47.17 | 56.15 | 10662.58 | 132930/143771 (92.5%) | ✅ | +| c128_i1024_o512 | 1024 | 512 | tp2_dp4 | 128 | 9.80 | 2483.34 | 1236.35 | 1486.37 | 47.72 | 59.20 | 70.21 | 26017.94 | 139322/143771 (96.9%) | ✅ | +| c128_i1024_o512 | 1024 | 512 | tp4_dp2 | 128 | 11.78 | 2986.46 | 996.03 | 1011.18 | 39.13 | 48.34 | 56.02 | 22283.80 | 139456/143771 (97.0%) | ✅ | +| c128_i1024_o512 | 1024 | 512 | tp8_dp1 | 128 | 17.09 | 4330.93 | 760.28 | 777.02 | 26.29 | 29.37 | 34.23 | 14073.81 | 132932/143771 (92.5%) | ✅ | +| c128_i1024_o1024 | 1024 | 1024 | tp2_dp4 | 128 | 7.08 | 3578.74 | 1147.11 | 1259.64 | 32.79 | 39.48 | 50.72 | 34693.91 | 139322/143771 (96.9%) | ✅ | +| c128_i1024_o1024 | 1024 | 1024 | tp4_dp2 | 128 | 8.62 | 4359.31 | 719.08 | 837.92 | 26.31 | 30.84 | 33.28 | 27367.26 | 139456/143771 (97.0%) | ✅ | +| c128_i1024_o1024 | 1024 | 1024 | tp8_dp1 | 128 | 9.35 | 4727.69 | 724.06 | 738.02 | 24.27 | 25.99 | 28.67 | 25355.91 | 132932/143771 (92.5%) | ✅ | +| c128_i1024_o2048 | 1024 | 2048 | tp2_dp4 | 128 | 4.40 | 4467.90 | 990.93 | 1038.67 | 25.24 | 28.25 | 31.35 | 52638.14 | 139322/143771 (96.9%) | ✅ | +| c128_i1024_o2048 | 1024 | 2048 | tp4_dp2 | 128 | 4.83 | 4909.69 | 979.55 | 1002.42 | 22.76 | 24.25 | 25.28 | 47303.18 | 139456/143771 (97.0%) | ✅ | +| c128_i1024_o2048 | 1024 | 2048 | tp8_dp1 | 128 | 4.80 | 4871.12 | 746.05 | 761.60 | 23.37 | 24.26 | 24.89 | 48201.59 | 132932/143771 (92.5%) | ✅ | +| c128_i1024_o4096 | 1024 | 4096 | tp2_dp4 | 128 | 2.42 | 4961.16 | 901.88 | 946.01 | 22.33 | 23.78 | 25.83 | 91949.11 | 139322/143771 (96.9%) | ✅ | +| c128_i1024_o4096 | 1024 | 4096 | tp4_dp2 | 128 | 2.49 | 5110.60 | 737.03 | 754.71 | 21.93 | 23.01 | 23.26 | 90427.39 | 139456/143771 (97.0%) | ✅ | +| c128_i1024_o4096 | 1024 | 4096 | tp8_dp1 | 128 | 2.33 | 4775.68 | 736.09 | 756.63 | 23.99 | 25.92 | 26.62 | 97316.79 | 132932/143771 (92.5%) | ✅ | + +## Best throughput per (ISL, DSL) + +| ISL | DSL | Best Config | Concurrency | OutTok/s | TTFT P95(ms) | TPOT Mean(ms) | SLO | +|---:|---:|---|---:|---:|---:|---:|---:| +| 1024 | 128 | tp8_dp1 | 128 | 1644.87 | 1647.93 | 71.51 | ⚠️ | +| 1024 | 256 | tp8_dp1 | 128 | 3082.56 | 725.46 | 37.61 | ✅ | +| 1024 | 512 | tp8_dp1 | 128 | 4330.93 | 760.28 | 26.29 | ✅ | +| 1024 | 1024 | tp8_dp1 | 128 | 4727.69 | 724.06 | 24.27 | ✅ | +| 1024 | 2048 | tp4_dp2 | 128 | 4909.69 | 979.55 | 22.76 | ✅ | +| 1024 | 4096 | tp4_dp2 | 128 | 5110.60 | 737.03 | 21.93 | ✅ | +| 4096 | 128 | tp8_dp1 | 64 | 772.92 | 2978.27 | 76.32 | ⚠️ | +| 4096 | 256 | tp8_dp1 | 64 | 2518.43 | 804.28 | 22.25 | ✅ | +| 4096 | 512 | tp8_dp1 | 64 | 3100.03 | 584.91 | 17.83 | ✅ | +| 4096 | 1024 | tp8_dp1 | 64 | 3283.93 | 789.79 | 17.06 | ✅ | +| 4096 | 2048 | tp8_dp1 | 64 | 3408.88 | 570.75 | 16.56 | ✅ | +| 4096 | 4096 | tp8_dp1 | 64 | 3408.94 | 576.41 | 16.44 | ✅ | +| 16384 | 128 | tp8_dp1 | 32 | 356.17 | 3789.36 | 78.86 | ❌ | +| 16384 | 256 | tp8_dp1 | 32 | 1782.54 | 636.48 | 14.84 | ✅ | +| 16384 | 512 | tp8_dp1 | 32 | 1977.19 | 640.86 | 14.04 | ✅ | +| 16384 | 1024 | tp8_dp1 | 32 | 2122.35 | 789.94 | 13.38 | ✅ | +| 16384 | 2048 | tp8_dp1 | 32 | 2226.25 | 628.02 | 12.88 | ✅ | +| 65536 | 128 | tp8_dp1 | 8 | 64.77 | 7445.34 | 88.42 | ❌ | +| 65536 | 256 | tp8_dp1 | 8 | 608.09 | 749.11 | 9.14 | ✅ | +| 65536 | 512 | tp8_dp1 | 8 | 705.69 | 661.39 | 9.10 | ✅ | +| 65536 | 1024 | tp8_dp1 | 8 | 734.78 | 671.08 | 8.91 | ✅ | +| 131072 | 128 | tp8_dp1 | 4 | 46.76 | 5665.45 | 46.92 | ⚠️ | +| 131072 | 256 | tp8_dp1 | 4 | 306.01 | 826.11 | 7.11 | ✅ | +| 131072 | 512 | tp8_dp1 | 4 | 382.40 | 581.21 | 7.67 | ✅ | +| 262144 | 128 | tp8_dp1 | 2 | 43.70 | 6405.29 | 12.04 | ⚠️ | +| 262144 | 256 | tp8_dp1 | 2 | 171.18 | 872.87 | 6.69 | ✅ | +| 524288 | 128 | tp8_dp1 | 2 | 133.35 | 1167.12 | 5.64 | ✅ | +| 1048576 | 128 | tp8_dp1 | 1 | 7.26 | 38265.96 | 4.67 | ⚠️ | + +## Notes + +- SLO check uses TTFT P95 and TPOT mean. +- A ⚠️ indicates one of the two metrics is out of target; ❌ indicates both are out. +- `Peak GPU mem` shows peak used / total MB and utilization percentage. +- Optional (P) combinations that failed are marked as skipped/OOM and do not break the run. diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/skipped_after_oom.csv b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/skipped_after_oom.csv new file mode 100644 index 0000000..46d89ab --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/skipped_after_oom.csv @@ -0,0 +1 @@ +engine,tp,dp,mark,isl,dsl,concurrency,status,reason,detail_log diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/report.md b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/report.md new file mode 100644 index 0000000..340263b --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/report.md @@ -0,0 +1,70 @@ +# 8x NVIDIA H200 143GB VLLM Benchmark Report + +- Result root: `/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4` +- Model: `/data/models/DeepSeek-V4-Flash` +- Backend: VLLM +- Benchmark client: `sglang.bench_serving --backend vllm` + +## Results + +| Scenario | Phase | Concurrency | Input | Output | Duration(s) | Success | Req/s | In tok/s | Out tok/s | Total tok/s | Mean TTFT(ms) | P95 TTFT(ms) | P99 TTFT(ms) | Mean TPOT(ms) | P95 TPOT(ms) | P99 TPOT(ms) | Mean E2E(ms) | P95 E2E(ms) | P99 E2E(ms) | Peak GPU mem | SLO | +|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| +| c1_i1024_o128 | main | 1 | 1024 | 128 | 4.76 | 5 | 1.05 | 373.68 | 79.65 | 453.33 | 159.97 | 319.08 | 355.57 | 10.56 | 10.99 | 11.00 | 950.14 | 1366.62 | 1406.84 | 138264/143771 MiB (96.2%) | ✅ | +| c128_i1024_o128 | main | 128 | 1024 | 128 | 45.42 | 640 | 14.09 | 7372.62 | 919.53 | 8292.15 | 682.86 | 1787.94 | 1815.68 | 131.99 | 159.76 | 191.60 | 8857.59 | 17800.52 | 19385.13 | 139322/143771 MiB (96.9%) | ⚠️ | +| c1_i1024_o256 | main | 1 | 1024 | 256 | 5.98 | 5 | 0.84 | 297.55 | 84.85 | 382.39 | 96.69 | 107.93 | 108.38 | 11.01 | 11.57 | 11.61 | 1193.49 | 1982.06 | 2082.56 | 139322/143771 MiB (96.9%) | ✅ | +| c128_i1024_o256 | main | 128 | 1024 | 256 | 51.15 | 640 | 12.51 | 6546.63 | 1654.84 | 8201.47 | 455.67 | 1302.99 | 1324.67 | 72.57 | 92.16 | 105.85 | 9769.30 | 18928.98 | 20487.34 | 139322/143771 MiB (96.9%) | ⚠️ | +| c1_i1024_o512 | main | 1 | 1024 | 512 | 6.34 | 5 | 0.79 | 280.27 | 79.92 | 360.18 | 95.33 | 113.71 | 115.02 | 11.50 | 11.85 | 11.86 | 1267.01 | 2173.11 | 2303.60 | 139322/143771 MiB (96.9%) | ✅ | +| c128_i1024_o512 | main | 128 | 1024 | 512 | 65.32 | 640 | 9.80 | 5126.38 | 2483.34 | 7609.72 | 392.20 | 1236.35 | 1486.37 | 47.72 | 59.20 | 70.21 | 12165.11 | 24348.08 | 26017.94 | 139322/143771 MiB (96.9%) | ✅ | +| c1_i1024_o1024 | main | 1 | 1024 | 1024 | 18.32 | 5 | 0.27 | 97.06 | 83.58 | 180.64 | 98.32 | 100.14 | 100.52 | 11.71 | 11.90 | 11.93 | 3661.85 | 8044.41 | 8200.76 | 139322/143771 MiB (96.9%) | ✅ | +| c128_i1024_o1024 | main | 128 | 1024 | 1024 | 90.39 | 640 | 7.08 | 3704.45 | 3578.74 | 7283.20 | 340.83 | 1147.11 | 1259.64 | 32.79 | 39.48 | 50.72 | 16393.11 | 32588.31 | 34693.91 | 139322/143771 MiB (96.9%) | ✅ | +| c1_i1024_o2048 | main | 1 | 1024 | 2048 | 66.40 | 5 | 0.08 | 26.78 | 84.74 | 111.51 | 95.99 | 105.11 | 105.45 | 11.70 | 11.81 | 11.81 | 13278.26 | 20062.55 | 20192.89 | 139322/143771 MiB (96.9%) | ✅ | +| c128_i1024_o2048 | main | 128 | 1024 | 2048 | 145.52 | 640 | 4.40 | 2301.16 | 4467.90 | 6769.06 | 282.02 | 990.93 | 1038.67 | 25.24 | 28.25 | 31.35 | 25564.98 | 48968.45 | 52638.14 | 139322/143771 MiB (96.9%) | ✅ | +| c1_i1024_o4096 | main | 1 | 1024 | 4096 | 136.81 | 5 | 0.04 | 13.00 | 86.04 | 99.04 | 98.28 | 114.24 | 116.37 | 11.59 | 11.84 | 11.86 | 27359.51 | 42290.37 | 43455.08 | 139322/143771 MiB (96.9%) | ✅ | +| c128_i1024_o4096 | main | 128 | 1024 | 4096 | 264.80 | 640 | 2.42 | 1264.57 | 4961.16 | 6225.74 | 265.10 | 901.88 | 946.01 | 22.33 | 23.78 | 25.83 | 45632.76 | 86442.33 | 91949.11 | 139322/143771 MiB (96.9%) | ✅ | +| c1_i4096_o128 | main | 1 | 4096 | 128 | 5.45 | 5 | 0.92 | 1829.89 | 69.56 | 1899.45 | 221.18 | 353.45 | 371.20 | 11.63 | 11.95 | 12.00 | 1088.26 | 1560.46 | 1608.68 | 139322/143771 MiB (96.9%) | ✅ | +| c64_i4096_o128 | main | 64 | 4096 | 128 | 29.05 | 320 | 11.02 | 23259.85 | 721.10 | 23980.95 | 566.58 | 1790.01 | 2034.19 | 83.97 | 111.62 | 188.61 | 5607.28 | 11212.93 | 12237.14 | 139324/143771 MiB (96.9%) | ⚠️ | +| c1_i4096_o256 | main | 1 | 4096 | 256 | 6.50 | 5 | 0.77 | 1534.00 | 78.01 | 1612.01 | 128.46 | 208.90 | 226.63 | 11.61 | 11.87 | 11.89 | 1298.45 | 2189.81 | 2296.91 | 139324/143771 MiB (96.9%) | ✅ | +| c64_i4096_o256 | main | 64 | 4096 | 256 | 37.63 | 320 | 8.50 | 17956.97 | 1101.01 | 19057.98 | 447.33 | 1290.52 | 1667.29 | 55.00 | 72.09 | 89.93 | 7132.99 | 14073.09 | 15631.13 | 139324/143771 MiB (96.9%) | ⚠️ | +| c1_i4096_o512 | main | 1 | 4096 | 512 | 6.48 | 5 | 0.77 | 1539.75 | 78.30 | 1618.05 | 124.97 | 210.04 | 232.13 | 11.63 | 11.95 | 11.98 | 1293.49 | 2240.30 | 2378.47 | 139324/143771 MiB (96.9%) | ✅ | +| c64_i4096_o512 | main | 64 | 4096 | 512 | 49.46 | 320 | 6.47 | 13661.57 | 1712.46 | 15374.03 | 363.21 | 1099.58 | 1280.63 | 32.92 | 40.95 | 51.15 | 9074.10 | 17834.26 | 18838.52 | 139324/143771 MiB (96.9%) | ✅ | +| c1_i4096_o1024 | main | 1 | 4096 | 1024 | 18.31 | 5 | 0.27 | 544.41 | 83.60 | 628.01 | 103.66 | 113.91 | 115.64 | 11.55 | 11.86 | 11.87 | 3661.10 | 8164.68 | 8360.74 | 139324/143771 MiB (96.9%) | ✅ | +| c64_i4096_o1024 | main | 64 | 4096 | 1024 | 72.82 | 320 | 4.39 | 9278.68 | 2351.38 | 11630.06 | 336.61 | 1083.22 | 1200.04 | 24.41 | 28.13 | 32.24 | 13050.59 | 25157.60 | 26088.66 | 139324/143771 MiB (96.9%) | ✅ | +| c1_i4096_o2048 | main | 1 | 4096 | 2048 | 65.21 | 5 | 0.08 | 152.90 | 86.30 | 239.20 | 107.97 | 122.31 | 124.03 | 11.54 | 11.75 | 11.78 | 13039.42 | 19438.63 | 19528.19 | 139324/143771 MiB (96.9%) | ✅ | +| c64_i4096_o2048 | main | 64 | 4096 | 2048 | 117.01 | 320 | 2.73 | 5774.33 | 2846.07 | 8620.40 | 297.64 | 1149.71 | 1194.86 | 19.80 | 22.43 | 24.96 | 20535.82 | 39745.31 | 41227.42 | 139324/143771 MiB (96.9%) | ✅ | +| c1_i4096_o4096 | main | 1 | 4096 | 4096 | 137.51 | 5 | 0.04 | 72.50 | 85.60 | 158.10 | 114.72 | 130.43 | 132.68 | 11.66 | 11.87 | 11.89 | 27500.53 | 42270.91 | 43588.26 | 139324/143771 MiB (96.9%) | ✅ | +| c64_i4096_o4096 | main | 64 | 4096 | 4096 | 214.54 | 320 | 1.49 | 3149.26 | 3050.95 | 6200.21 | 274.73 | 900.93 | 999.74 | 17.93 | 19.28 | 20.04 | 36687.19 | 72324.60 | 75036.72 | 139324/143771 MiB (96.9%) | ✅ | +| c1_i16384_o128 | main | 1 | 16384 | 128 | 5.71 | 5 | 0.88 | 7481.41 | 66.35 | 7547.76 | 320.96 | 599.10 | 618.22 | 11.00 | 11.48 | 11.54 | 1140.76 | 1856.53 | 1948.72 | 139324/143771 MiB (96.9%) | ✅ | +| c32_i16384_o128 | main | 32 | 16384 | 128 | 37.11 | 160 | 4.31 | 34791.25 | 284.72 | 35075.97 | 956.28 | 3298.27 | 4051.80 | 107.21 | 186.59 | 376.91 | 7222.82 | 13755.15 | 15245.93 | 139324/143771 MiB (96.9%) | ❌ | +| c1_i16384_o256 | main | 1 | 16384 | 256 | 7.07 | 5 | 0.71 | 6043.42 | 71.69 | 6115.12 | 256.48 | 448.96 | 486.54 | 11.52 | 11.66 | 11.67 | 1412.57 | 2447.12 | 2621.34 | 139324/143771 MiB (96.9%) | ✅ | +| c32_i16384_o256 | main | 32 | 16384 | 256 | 35.65 | 160 | 4.49 | 36211.60 | 623.03 | 36834.63 | 680.08 | 1913.91 | 2384.97 | 47.34 | 71.67 | 147.97 | 6749.38 | 12780.12 | 13936.33 | 139684/143771 MiB (97.2%) | ✅ | +| c1_i16384_o512 | main | 1 | 16384 | 512 | 6.52 | 5 | 0.77 | 6550.19 | 77.70 | 6627.89 | 139.05 | 188.54 | 190.96 | 11.55 | 11.73 | 11.74 | 1303.13 | 2227.30 | 2356.50 | 139684/143771 MiB (97.2%) | ✅ | +| c32_i16384_o512 | main | 32 | 16384 | 512 | 42.41 | 160 | 3.77 | 30447.27 | 952.48 | 31399.75 | 538.18 | 1520.07 | 2259.12 | 30.21 | 45.07 | 57.04 | 7937.47 | 16413.95 | 18769.12 | 139684/143771 MiB (97.2%) | ✅ | +| c1_i16384_o1024 | main | 1 | 16384 | 1024 | 18.25 | 5 | 0.27 | 2341.54 | 83.88 | 2425.42 | 188.47 | 322.92 | 349.35 | 11.31 | 11.64 | 11.64 | 3648.93 | 7809.61 | 7915.88 | 139684/143771 MiB (97.2%) | ✅ | +| c32_i16384_o1024 | main | 32 | 16384 | 1024 | 63.50 | 160 | 2.52 | 20332.49 | 1337.54 | 21670.03 | 485.63 | 1871.97 | 2404.37 | 22.95 | 27.86 | 72.28 | 11657.91 | 21919.16 | 22977.81 | 139684/143771 MiB (97.2%) | ✅ | +| c1_i16384_o2048 | main | 1 | 16384 | 2048 | 65.72 | 5 | 0.08 | 650.30 | 85.62 | 735.91 | 175.36 | 249.46 | 261.08 | 11.54 | 11.64 | 11.65 | 13142.27 | 19985.51 | 20210.50 | 139684/143771 MiB (97.2%) | ✅ | +| c32_i16384_o2048 | main | 32 | 16384 | 2048 | 102.63 | 160 | 1.56 | 12580.64 | 1785.47 | 14366.11 | 336.45 | 1089.13 | 1111.26 | 15.83 | 17.47 | 19.70 | 18450.05 | 31359.53 | 33430.94 | 139684/143771 MiB (97.2%) | ✅ | +| c1_i65536_o128 | main | 1 | 65536 | 128 | 11.40 | 5 | 0.44 | 15249.82 | 33.25 | 15283.07 | 1429.50 | 2811.65 | 2892.88 | 11.47 | 12.08 | 12.21 | 2278.14 | 4059.40 | 4233.91 | 139706/143771 MiB (97.2%) | ✅ | +| c8_i65536_o128 | main | 8 | 65536 | 128 | 46.50 | 40 | 0.86 | 31649.77 | 55.23 | 31705.00 | 2642.31 | 5855.87 | 7061.54 | 115.39 | 327.74 | 399.92 | 9193.45 | 17992.56 | 18685.86 | 139708/143771 MiB (97.2%) | ❌ | +| c1_i65536_o256 | main | 1 | 65536 | 256 | 10.35 | 5 | 0.48 | 16785.56 | 48.96 | 16834.52 | 902.47 | 2181.49 | 2314.91 | 11.55 | 11.95 | 11.96 | 2069.19 | 3540.82 | 3709.96 | 139708/143771 MiB (97.2%) | ✅ | +| c8_i65536_o256 | main | 8 | 65536 | 256 | 44.64 | 40 | 0.90 | 32962.95 | 117.73 | 33080.69 | 1800.38 | 4029.43 | 4806.74 | 54.45 | 101.30 | 122.71 | 8621.68 | 16550.72 | 18052.15 | 139708/143771 MiB (97.2%) | ❌ | +| c1_i65536_o512 | main | 1 | 65536 | 512 | 8.02 | 5 | 0.62 | 21662.85 | 63.19 | 21726.04 | 501.88 | 1276.37 | 1453.96 | 11.06 | 11.68 | 11.78 | 1602.98 | 2564.65 | 2624.42 | 139708/143771 MiB (97.2%) | ✅ | +| c8_i65536_o512 | main | 8 | 65536 | 512 | 40.84 | 40 | 0.98 | 36028.75 | 272.84 | 36301.59 | 1260.91 | 3168.19 | 5671.91 | 24.56 | 51.52 | 85.56 | 7629.47 | 14481.52 | 18250.24 | 139708/143771 MiB (97.2%) | ⚠️ | +| c1_i65536_o1024 | main | 1 | 65536 | 1024 | 18.42 | 5 | 0.27 | 9437.05 | 83.13 | 9520.17 | 255.57 | 375.58 | 383.90 | 11.12 | 11.57 | 11.58 | 3681.79 | 8015.79 | 8213.89 | 139708/143771 MiB (97.2%) | ✅ | +| c8_i65536_o1024 | main | 8 | 65536 | 1024 | 62.34 | 40 | 0.64 | 23606.18 | 351.24 | 23957.42 | 962.35 | 2850.09 | 2967.29 | 19.43 | 29.44 | 36.68 | 11157.95 | 21105.82 | 21507.37 | 139708/143771 MiB (97.2%) | ✅ | +| c1_i131072_o128 | main | 1 | 131072 | 128 | 15.53 | 5 | 0.32 | 23847.78 | 24.40 | 23872.18 | 2286.42 | 3831.71 | 3847.18 | 11.06 | 11.65 | 11.68 | 3104.64 | 4990.35 | 5071.55 | 140228/143771 MiB (97.5%) | ⚠️ | +| c4_i131072_o128 | main | 4 | 131072 | 128 | 27.14 | 20 | 0.74 | 54328.24 | 41.97 | 54370.21 | 2648.47 | 5381.79 | 6485.26 | 63.46 | 234.23 | 254.36 | 5273.33 | 9530.16 | 9800.84 | 140228/143771 MiB (97.5%) | ❌ | +| c1_i131072_o256 | main | 1 | 131072 | 256 | 10.82 | 5 | 0.46 | 34222.74 | 46.84 | 34269.59 | 1053.51 | 3143.30 | 3630.53 | 11.11 | 11.90 | 11.97 | 2162.71 | 4514.33 | 4950.01 | 140228/143771 MiB (97.5%) | ⚠️ | +| c4_i131072_o256 | main | 4 | 131072 | 256 | 39.32 | 20 | 0.51 | 37498.25 | 64.78 | 37563.03 | 2168.98 | 4431.12 | 6485.73 | 38.02 | 82.59 | 93.31 | 7621.59 | 19293.47 | 21326.10 | 140228/143771 MiB (97.5%) | ⚠️ | +| c1_i131072_o512 | main | 1 | 131072 | 512 | 7.44 | 5 | 0.67 | 49763.22 | 68.11 | 49831.33 | 391.27 | 574.50 | 577.45 | 10.89 | 11.54 | 11.54 | 1487.11 | 2243.60 | 2318.95 | 140228/143771 MiB (97.5%) | ✅ | +| c4_i131072_o512 | main | 4 | 131072 | 512 | 43.08 | 20 | 0.46 | 34227.86 | 136.39 | 34364.24 | 1588.49 | 5162.58 | 5751.13 | 24.26 | 43.94 | 51.73 | 8028.29 | 13969.64 | 14391.10 | 140228/143771 MiB (97.5%) | ⚠️ | +| c1_i262144_o128 | main | 1 | 262144 | 128 | 33.40 | 5 | 0.15 | 22865.42 | 11.35 | 22876.77 | 5896.15 | 13444.27 | 14788.12 | 9.88 | 11.09 | 11.15 | 6677.66 | 14582.28 | 16032.30 | 140744/143771 MiB (97.9%) | ⚠️ | +| c2_i262144_o128 | main | 2 | 262144 | 128 | 36.61 | 10 | 0.27 | 38069.90 | 20.65 | 38090.55 | 4480.80 | 9292.65 | 9433.23 | 24.30 | 74.40 | 75.57 | 6665.65 | 10320.34 | 10323.72 | 140744/143771 MiB (97.9%) | ⚠️ | +| c1_i262144_o256 | main | 1 | 262144 | 256 | 27.87 | 5 | 0.18 | 27404.52 | 18.19 | 27422.71 | 4494.81 | 8943.43 | 9385.72 | 10.07 | 11.43 | 11.50 | 5571.33 | 10356.69 | 10671.30 | 141258/143771 MiB (98.3%) | ⚠️ | +| c2_i262144_o256 | main | 2 | 262144 | 256 | 33.18 | 10 | 0.30 | 42010.29 | 42.07 | 42052.36 | 2785.85 | 9153.02 | 10642.68 | 24.92 | 66.10 | 74.81 | 6437.85 | 12049.75 | 12104.02 | 141258/143771 MiB (98.3%) | ⚠️ | +| c1_i524288_o128 | main | 1 | 524288 | 128 | 38.85 | 5 | 0.13 | 26404.42 | 9.76 | 26414.18 | 7011.27 | 17139.22 | 19091.80 | 9.70 | 10.39 | 10.40 | 7768.26 | 18082.00 | 20099.12 | 141258/143771 MiB (98.3%) | ⚠️ | +| c2_i524288_o128 | main | 2 | 524288 | 128 | 14.47 | 10 | 0.69 | 114432.83 | 52.24 | 114485.07 | 1445.03 | 4695.87 | 6463.46 | 15.77 | 44.14 | 65.40 | 2876.67 | 7604.53 | 8060.58 | 141258/143771 MiB (98.3%) | ⚠️ | +| c1_i1048576_o128 | main | 1 | 1048576 | 128 | 78.14 | 5 | 0.06 | 19836.89 | 4.85 | 19841.74 | 14906.36 | 46081.66 | 51394.85 | 8.95 | 10.50 | 10.51 | 15626.56 | 46632.30 | 51849.45 | 141258/143771 MiB (98.3%) | ⚠️ | +| c2_i1048576_o128 | main | 2 | 1048576 | 128 | 181.75 | 10 | 0.06 | 17765.33 | 4.16 | 17769.49 | 24258.31 | 61414.70 | 65340.99 | 117.07 | 500.43 | 531.18 | 30965.88 | 62664.75 | 66294.91 | 141780/143771 MiB (98.6%) | ❌ | + +SLO: S2 tier — TTFT P95 < 3000ms, TPOT mean < 50ms. ✅ pass, ⚠️ partial, ❌ fail. + diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/results.json b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/results.json new file mode 100644 index 0000000..114a410 --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/results.json @@ -0,0 +1,3500 @@ +{ + "metadata": { + "experiment": "dsv4_h200_vllm_tp_dp_matrix_tp2_dp4", + "run_id": "20260709-152419_matrix", + "timestamp": "2026-07-09T15:24:26+00:00", + "model": "/data/models/DeepSeek-V4-Flash", + "backend": "vllm", + "engine": "vllm", + "hardware": "8x NVIDIA H200 143GB", + "accelerator": "NVIDIA H200", + "chip": "nvidia_h200", + "script": "experiments/dsv4_h200_vllm_tp_dp_matrix/run_bench.sh", + "env": "/data/user1/yy/envs/vllm", + "git_commit": "6fce89c", + "git_dirty": "dirty", + "description": "H200 vLLM TP×DP matrix for DeepSeek-V4-Flash" + }, + "config": { + "tp": 2, + "dp": 4, + "cuda_visible_devices": "0,1,2,3,4,5,6,7", + "backend": "vllm", + "server_start_script": "experiments/dsv4_h200_vllm_tp_dp_matrix/start_vllm_dp.sh", + "server_args": "vllm serve /data/models/DeepSeek-V4-Flash --trust-remote-code --kv-cache-dtype fp8 --block-size 256 --tensor-parallel-size 2 --no-enable-flashinfer-autotune --port 30030 --data-parallel-size 4 " + }, + "scenarios": [ + { + "name": "c1_i1024_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.758116067008814, + "request_throughput": 1.050836072425456, + "input_token_throughput": 373.6773073544922, + "output_token_throughput": 79.65337428984957, + "total_token_throughput": 453.3306816443417, + "total_input_tokens": 1778, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 950.1402601948939, + "p50": 828.8744620222133, + "p90": 1316.3475427834783, + "p95": 1366.620513383532, + "p99": 1406.8388898635749 + }, + "ttft_ms": { + "mean": 159.96879799640737, + "p50": 121.72545900102705, + "p90": 273.4667629993055, + "p95": 319.0807249920908, + "p99": 355.5718945863191 + }, + "tpot_ms": { + "mean": 10.561727335790406, + "p50": 10.597711921482365, + "p90": 10.980906958036579, + "p95": 10.992017729171314, + "p99": 11.0009063460791 + }, + "itl_ms": { + "mean": 10.563021828840675, + "p50": 10.395356992376037, + "p90": 11.467909900238737, + "p95": 12.289851512468884, + "p99": 17.385886098782056 + }, + "gpu_memory": { + "peak_used_mb": 138264.0, + "avg_used_mb": 138239.14285714284, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_1024_128.jsonl" + }, + { + "name": "c128_i1024_o128", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 128, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 45.41872370798956, + "request_throughput": 14.091104895741893, + "input_token_throughput": 7372.620202911955, + "output_token_throughput": 919.5326638527569, + "total_token_throughput": 8292.152866764713, + "total_input_tokens": 334855, + "total_output_tokens": 41764, + "e2e_ms": { + "mean": 8857.588239907182, + "p50": 8342.36057351518, + "p90": 16634.871855200618, + "p95": 17800.523617253926, + "p99": 19385.132683189295 + }, + "ttft_ms": { + "mean": 682.8604170356357, + "p50": 574.7430620103842, + "p90": 1326.4753445982933, + "p95": 1787.9390910849907, + "p99": 1815.6773361668456 + }, + "tpot_ms": { + "mean": 131.98884306108397, + "p50": 139.4344896548215, + "p90": 154.4109195061627, + "p95": 159.76067048531368, + "p99": 191.59725015624025 + }, + "itl_ms": { + "mean": 127.26984535282504, + "p50": 80.08746500127017, + "p90": 209.82746919326036, + "p95": 320.7620121524087, + "p99": 333.84307554457337 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 138885.82142857142, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_128_1024_128.jsonl" + }, + { + "name": "c1_i1024_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 5.975539081002353, + "request_throughput": 0.8367445902740689, + "input_token_throughput": 297.5463763014589, + "output_token_throughput": 84.84590145379059, + "total_token_throughput": 382.3922777552495, + "total_input_tokens": 1778, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1193.4936490026303, + "p50": 1250.7776489946991, + "p90": 1856.4413986110594, + "p95": 1982.0633718161841, + "p99": 2082.5609503802843 + }, + "ttft_ms": { + "mean": 96.69496160349809, + "p50": 101.44926799694076, + "p90": 107.36800140584819, + "p95": 107.92980521218851, + "p99": 108.37924825726077 + }, + "tpot_ms": { + "mean": 11.009321936568274, + "p50": 11.267925303899592, + "p90": 11.515062654038317, + "p95": 11.568587976709885, + "p99": 11.61140823484714 + }, + "itl_ms": { + "mean": 10.923821774990376, + "p50": 10.853135987417772, + "p90": 11.97037369129248, + "p95": 12.5487451616209, + "p99": 15.062141394300852 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139312.0, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_1024_256.jsonl" + }, + { + "name": "c128_i1024_o256", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 256, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 51.14925201400183, + "request_throughput": 12.512401937467306, + "input_token_throughput": 6546.625548079085, + "output_token_throughput": 1654.8433587421603, + "total_token_throughput": 8201.468906821246, + "total_input_tokens": 334855, + "total_output_tokens": 84644, + "e2e_ms": { + "mean": 9769.298043770004, + "p50": 9525.109273497947, + "p90": 17658.252803297364, + "p95": 18928.978795289004, + "p99": 20487.34497815196 + }, + "ttft_ms": { + "mean": 455.66914050150444, + "p50": 347.1923780016368, + "p90": 1053.0307672161146, + "p95": 1302.987777524686, + "p99": 1324.667504846293 + }, + "tpot_ms": { + "mean": 72.5739601324665, + "p50": 75.14341008104658, + "p90": 88.30012603298934, + "p95": 92.16179340800115, + "p99": 105.85343872891032 + }, + "itl_ms": { + "mean": 70.98191771984622, + "p50": 29.792312008794397, + "p90": 188.3531395928003, + "p95": 192.85231040557846, + "p99": 200.51675533934022 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139312.4455128205, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_128_1024_256.jsonl" + }, + { + "name": "c1_i1024_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 6.343974668008741, + "request_throughput": 0.788149427079823, + "input_token_throughput": 280.2659362695851, + "output_token_throughput": 79.91835190589406, + "total_token_throughput": 360.18428817547914, + "total_input_tokens": 1778, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1267.0076036010869, + "p50": 1300.423595996108, + "p90": 2010.006586799864, + "p95": 2173.1115423957817, + "p99": 2303.595506872516 + }, + "ttft_ms": { + "mean": 95.3274762025103, + "p50": 94.37420600443147, + "p90": 112.07389460178092, + "p95": 113.70997279882431, + "p99": 115.01883535645902 + }, + "tpot_ms": { + "mean": 11.499225230518311, + "p50": 11.818655644599271, + "p90": 11.843597487057481, + "p95": 11.85012544028685, + "p99": 11.855347802870343 + }, + "itl_ms": { + "mean": 11.669650207161421, + "p50": 11.596686512348242, + "p90": 12.528862190083602, + "p95": 13.203412367147392, + "p99": 15.747690293937925 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_1024_512.jsonl" + }, + { + "name": "c128_i1024_o512", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 512, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 65.32000953899114, + "request_throughput": 9.797916511600752, + "input_token_throughput": 5126.377083581359, + "output_token_throughput": 2483.3431768434084, + "total_token_throughput": 7609.720260424768, + "total_input_tokens": 334855, + "total_output_tokens": 162212, + "e2e_ms": { + "mean": 12165.105242891741, + "p50": 11360.551028003101, + "p90": 22530.299117119284, + "p95": 24348.07764037541, + "p99": 26017.943218774457 + }, + "ttft_ms": { + "mean": 392.20384273189666, + "p50": 257.13926850585267, + "p90": 1188.2762587134494, + "p95": 1236.3547743909294, + "p99": 1486.3738604661194 + }, + "tpot_ms": { + "mean": 47.71833474125024, + "p50": 49.15205960397588, + "p90": 55.67882519789395, + "p95": 59.20219377536446, + "p99": 70.21163779017805 + }, + "itl_ms": { + "mean": 46.65614312299236, + "p50": 23.88978801900521, + "p90": 171.87037938274446, + "p95": 179.28580839652565, + "p99": 194.64230959885745 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_128_1024_512.jsonl" + }, + { + "name": "c1_i1024_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 18.318240207008785, + "request_throughput": 0.2729519835691934, + "input_token_throughput": 97.06172535720518, + "output_token_throughput": 83.57789736888702, + "total_token_throughput": 180.6396227260922, + "total_input_tokens": 1778, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 3661.845855199499, + "p50": 1542.1712879906408, + "p90": 7848.975591792259, + "p95": 8044.409900391475, + "p99": 8200.757347270846 + }, + "ttft_ms": { + "mean": 98.31969080260023, + "p50": 97.93389998958446, + "p90": 99.6642264071852, + "p95": 100.14198120916262, + "p99": 100.52418505074456 + }, + "tpot_ms": { + "mean": 11.7121814298879, + "p50": 11.669991084686192, + "p90": 11.861798871547494, + "p95": 11.897594997713366, + "p99": 11.926231898646064 + }, + "itl_ms": { + "mean": 11.675879083884157, + "p50": 11.550955998245627, + "p90": 12.462123500881717, + "p95": 12.981617015611846, + "p99": 15.28279174817726 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_1024_1024.jsonl" + }, + { + "name": "c128_i1024_o1024", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 1024, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 90.39259965502424, + "request_throughput": 7.080225620709065, + "input_token_throughput": 3704.451484722709, + "output_token_throughput": 3578.744291397526, + "total_token_throughput": 7283.195776120236, + "total_input_tokens": 334855, + "total_output_tokens": 323492, + "e2e_ms": { + "mean": 16393.11319388412, + "p50": 15487.006908500916, + "p90": 30442.54000379297, + "p95": 32588.307497503407, + "p99": 34693.91080739064 + }, + "ttft_ms": { + "mean": 340.82878647768666, + "p50": 182.82538150378969, + "p90": 1101.2389173178235, + "p95": 1147.1085372351808, + "p99": 1259.63883144781 + }, + "tpot_ms": { + "mean": 32.786099067756574, + "p50": 33.33336248642041, + "p90": 38.46325583622135, + "p95": 39.48297626561873, + "p99": 50.717053920294475 + }, + "itl_ms": { + "mean": 31.838508019006326, + "p50": 20.308328996179625, + "p90": 51.352259801933535, + "p95": 67.75311281671735, + "p99": 189.77136611239962 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_128_1024_1024.jsonl" + }, + { + "name": "c1_i1024_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 66.40485374600394, + "request_throughput": 0.07529570081013673, + "input_token_throughput": 26.775151208084623, + "output_token_throughput": 84.73778169172787, + "total_token_throughput": 111.5129328998125, + "total_input_tokens": 1778, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 13278.26379040489, + "p50": 12816.862097999547, + "p90": 19899.61227281019, + "p95": 20062.545839411905, + "p99": 20192.892692693276 + }, + "ttft_ms": { + "mean": 95.99211560562253, + "p50": 98.21665400522761, + "p90": 104.68877339735627, + "p95": 105.11285619577393, + "p99": 105.45212243450806 + }, + "tpot_ms": { + "mean": 11.699930378375884, + "p50": 11.67477062993357, + "p90": 11.8023444723689, + "p95": 11.807400475164444, + "p99": 11.811445277400878 + }, + "itl_ms": { + "mean": 11.723782554422815, + "p50": 11.635283488431014, + "p90": 12.452087798737923, + "p95": 12.916478484112302, + "p99": 15.040395660907961 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_1024_2048.jsonl" + }, + { + "name": "c128_i1024_o2048", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 2048, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 145.51546835299814, + "request_throughput": 4.3981578538953565, + "input_token_throughput": 2301.1642940095776, + "output_token_throughput": 4467.896144366185, + "total_token_throughput": 6769.060438375763, + "total_input_tokens": 334855, + "total_output_tokens": 650148, + "e2e_ms": { + "mean": 25564.97701632352, + "p50": 25074.268465992645, + "p90": 44908.9447277016, + "p95": 48968.45160179073, + "p99": 52638.13623400958 + }, + "ttft_ms": { + "mean": 282.0233969084711, + "p50": 119.06985749374144, + "p90": 974.8386680934345, + "p95": 990.9265333903022, + "p99": 1038.6707634397317 + }, + "tpot_ms": { + "mean": 25.236928190194135, + "p50": 26.040975281755923, + "p90": 27.663812289644483, + "p95": 28.25427095289195, + "p99": 31.35192731330995 + }, + "itl_ms": { + "mean": 24.927056339505796, + "p50": 20.130142016569152, + "p90": 29.90092160762288, + "p95": 49.22005442203953, + "p99": 175.35870163235813 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_128_1024_2048.jsonl" + }, + { + "name": "c1_i1024_o4096", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 4096, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 136.8059436570038, + "request_throughput": 0.03654811966748949, + "input_token_throughput": 12.996511353759264, + "output_token_throughput": 86.04158332120376, + "total_token_throughput": 99.03809467496302, + "total_input_tokens": 1778, + "total_output_tokens": 11771, + "e2e_ms": { + "mean": 27359.510401409352, + "p50": 24717.59735699743, + "p90": 40834.48683540337, + "p95": 42290.37321120268, + "p99": 43455.082311842125 + }, + "ttft_ms": { + "mean": 98.28299639630131, + "p50": 102.85077299340628, + "p90": 111.57594778924249, + "p95": 114.23956138896756, + "p99": 116.37045226874761 + }, + "tpot_ms": { + "mean": 11.5920802460413, + "p50": 11.570362888125286, + "p90": 11.822217032060614, + "p95": 11.844249215126016, + "p99": 11.861874961578337 + }, + "itl_ms": { + "mean": 11.584727219787979, + "p50": 11.493468991830014, + "p90": 12.399183004163206, + "p95": 12.895709507574793, + "p99": 14.916132208600175 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_1024_4096.jsonl" + }, + { + "name": "c128_i1024_o4096", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 4096, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 264.796780818986, + "request_throughput": 2.416947811905241, + "input_token_throughput": 1264.573530555515, + "output_token_throughput": 4961.163032031118, + "total_token_throughput": 6225.736562586633, + "total_input_tokens": 334855, + "total_output_tokens": 1313700, + "e2e_ms": { + "mean": 45632.76200614837, + "p50": 45892.894881995744, + "p90": 80464.02358178457, + "p95": 86442.33155561086, + "p99": 91949.11381047481 + }, + "ttft_ms": { + "mean": 265.10322853509933, + "p50": 111.98848400090355, + "p90": 881.7293376894668, + "p95": 901.8796355012455, + "p99": 946.0079092771048 + }, + "tpot_ms": { + "mean": 22.32576383160298, + "p50": 22.827393246859977, + "p90": 23.463852907171333, + "p95": 23.78087823866866, + "p99": 25.827674788164533 + }, + "itl_ms": { + "mean": 22.124532073000303, + "p50": 20.05979197565466, + "p90": 23.99035880225711, + "p95": 30.73016601265389, + "p99": 61.827885597012774 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_128_1024_4096.jsonl" + }, + { + "name": "c1_i4096_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 5.4484130880155135, + "request_throughput": 0.9176984048801556, + "input_token_throughput": 1829.8906193310304, + "output_token_throughput": 69.5615390899158, + "total_token_throughput": 1899.4521584209463, + "total_input_tokens": 9970, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 1088.2617171911988, + "p50": 1180.7936400000472, + "p90": 1500.1804889994673, + "p95": 1560.4593069991097, + "p99": 1608.6823613988236 + }, + "ttft_ms": { + "mean": 221.18209359468892, + "p50": 237.3110229964368, + "p90": 331.26449820119893, + "p95": 353.4522086090874, + "p99": 371.2023769353982 + }, + "tpot_ms": { + "mean": 11.62819634498916, + "p50": 11.65763964963844, + "p90": 11.887479798249698, + "p95": 11.952572407454307, + "p99": 12.004646494817992 + }, + "itl_ms": { + "mean": 11.591416058758707, + "p50": 11.50220850831829, + "p90": 12.546429494977929, + "p95": 13.778341589204501, + "p99": 15.210930389293933 + }, + "gpu_memory": { + "peak_used_mb": 139322.0, + "avg_used_mb": 139314.0, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_4096_128.jsonl" + }, + { + "name": "c64_i4096_o128", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 128, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 29.04734625099809, + "request_throughput": 11.01649690250119, + "input_token_throughput": 23259.85286785999, + "output_token_throughput": 721.0985753743436, + "total_token_throughput": 23980.95144323433, + "total_input_tokens": 675637, + "total_output_tokens": 20946, + "e2e_ms": { + "mean": 5607.2807608573385, + "p50": 5081.751556514064, + "p90": 10261.717318402958, + "p95": 11212.930104890256, + "p99": 12237.140612378425 + }, + "ttft_ms": { + "mean": 566.5797051917252, + "p50": 418.8897180138156, + "p90": 1271.789528624504, + "p95": 1790.0078742284677, + "p99": 2034.1907628765327 + }, + "tpot_ms": { + "mean": 83.97221397509522, + "p50": 85.30900120052598, + "p90": 102.1884308779788, + "p95": 111.6186297058448, + "p99": 188.61308130843136 + }, + "itl_ms": { + "mean": 78.22580327691779, + "p50": 24.40394448058214, + "p90": 193.86407711426727, + "p95": 204.7966962083592, + "p99": 265.26391156658065 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139315.09433962265, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_64_4096_128.jsonl" + }, + { + "name": "c1_i4096_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 6.499336033011787, + "request_throughput": 0.7693093532329647, + "input_token_throughput": 1534.0028503465317, + "output_token_throughput": 78.00796841782262, + "total_token_throughput": 1612.010818764354, + "total_input_tokens": 9970, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1298.4541277983226, + "p50": 1304.8905359755736, + "p90": 2055.9390532027464, + "p95": 2189.8132465954404, + "p99": 2296.9126013095956 + }, + "ttft_ms": { + "mean": 128.45938939717598, + "p50": 99.99181900639087, + "p90": 186.73655440798032, + "p95": 208.8984222093131, + "p99": 226.62791645037942 + }, + "tpot_ms": { + "mean": 11.608829012618783, + "p50": 11.749471700750291, + "p90": 11.840187970346939, + "p95": 11.866101362627823, + "p99": 11.886832076452531 + }, + "itl_ms": { + "mean": 11.652879141557746, + "p50": 11.607007996644825, + "p90": 12.479607487330213, + "p95": 13.407818757696077, + "p99": 15.573228679131718 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139316.5, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_4096_256.jsonl" + }, + { + "name": "c64_i4096_o256", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 256, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 37.625335443997756, + "request_throughput": 8.504907563582892, + "input_token_throughput": 17956.96947355142, + "output_token_throughput": 1101.0134397780778, + "total_token_throughput": 19057.9829133295, + "total_input_tokens": 675637, + "total_output_tokens": 41426, + "e2e_ms": { + "mean": 7132.9945801561735, + "p50": 6745.084112990298, + "p90": 13343.782691296656, + "p95": 14073.086364858318, + "p99": 15631.130007481263 + }, + "ttft_ms": { + "mean": 447.32724439654703, + "p50": 292.0360850112047, + "p90": 1235.394539491972, + "p95": 1290.521132601134, + "p99": 1667.2943222423783 + }, + "tpot_ms": { + "mean": 54.999285976148414, + "p50": 56.64399173060109, + "p90": 66.60206160047979, + "p95": 72.08972101296075, + "p99": 89.93224260194778 + }, + "itl_ms": { + "mean": 52.06885576994, + "p50": 20.320953015470877, + "p90": 183.50273961550556, + "p95": 190.4936825420009, + "p99": 198.8381153621594 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139316.71376811594, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_64_4096_256.jsonl" + }, + { + "name": "c1_i4096_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 6.4750854239973705, + "request_throughput": 0.7721905847711995, + "input_token_throughput": 1539.7480260337718, + "output_token_throughput": 78.30012529579963, + "total_token_throughput": 1618.0481513295715, + "total_input_tokens": 9970, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1293.4944579959847, + "p50": 1285.3574529872276, + "p90": 2067.5757369899657, + "p95": 2240.2964659850113, + "p99": 2378.473049181048 + }, + "ttft_ms": { + "mean": 124.96559479623102, + "p50": 99.54141901107505, + "p90": 182.4217675952241, + "p95": 210.03611879423258, + "p99": 232.1275997534394 + }, + "tpot_ms": { + "mean": 11.633153599071646, + "p50": 11.704481980368477, + "p90": 11.917797849731988, + "p95": 11.949951966215707, + "p99": 11.97567525940268 + }, + "itl_ms": { + "mean": 11.638103784917691, + "p50": 11.591274989768863, + "p90": 12.394777726149186, + "p95": 12.914686684962362, + "p99": 15.002317985636184 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_4096_512.jsonl" + }, + { + "name": "c64_i4096_o512", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 512, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 49.45528774798731, + "request_throughput": 6.470491115745719, + "input_token_throughput": 13661.572518653407, + "output_token_throughput": 1712.4559143515778, + "total_token_throughput": 15374.028433004985, + "total_input_tokens": 675637, + "total_output_tokens": 84690, + "e2e_ms": { + "mean": 9074.096850075239, + "p50": 8587.769280493376, + "p90": 16507.49469749572, + "p95": 17834.255616509472, + "p99": 18838.51776815718 + }, + "ttft_ms": { + "mean": 363.21495642187074, + "p50": 246.24972649326082, + "p90": 1080.8688154967967, + "p95": 1099.5816637849202, + "p99": 1280.63276574685 + }, + "tpot_ms": { + "mean": 32.92398170254894, + "p50": 34.29781718488103, + "p90": 39.79399375426641, + "p95": 40.95253786620741, + "p99": 51.14963246416302 + }, + "itl_ms": { + "mean": 33.051612037932166, + "p50": 16.917625995120034, + "p90": 55.95782760065051, + "p95": 179.05423378688283, + "p99": 191.79221595288254 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_64_4096_512.jsonl" + }, + { + "name": "c1_i4096_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 18.313489350985037, + "request_throughput": 0.27302279233482407, + "input_token_throughput": 544.4074479156392, + "output_token_throughput": 83.59957901292313, + "total_token_throughput": 628.0070269285624, + "total_input_tokens": 9970, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 3661.097132199211, + "p50": 1497.5465280003846, + "p90": 7919.612569594756, + "p95": 8164.683188794878, + "p99": 8360.739684154978 + }, + "ttft_ms": { + "mean": 103.66270020604134, + "p50": 101.5966720005963, + "p90": 111.75517840893008, + "p95": 113.91170821152627, + "p99": 115.63693205360323 + }, + "tpot_ms": { + "mean": 11.545292009534641, + "p50": 11.536920022783296, + "p90": 11.859975367734606, + "p95": 11.863926409369533, + "p99": 11.867087242677476 + }, + "itl_ms": { + "mean": 11.655896806018823, + "p50": 11.571258990443312, + "p90": 12.372287004836835, + "p95": 12.828694510972127, + "p99": 15.069960492837708 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_4096_1024.jsonl" + }, + { + "name": "c64_i4096_o1024", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 1024, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 72.81607443501707, + "request_throughput": 4.394634048634085, + "input_token_throughput": 9278.679264740585, + "output_token_throughput": 2351.3764141844713, + "total_token_throughput": 11630.055678925057, + "total_input_tokens": 675637, + "total_output_tokens": 171218, + "e2e_ms": { + "mean": 13050.591836434796, + "p50": 13009.477967498242, + "p90": 23550.056274895916, + "p95": 25157.595743636197, + "p99": 26088.66373818193 + }, + "ttft_ms": { + "mean": 336.6113820809005, + "p50": 228.19460948812775, + "p90": 1073.0186230968684, + "p95": 1083.2181056088302, + "p99": 1200.0421604982694 + }, + "tpot_ms": { + "mean": 24.405185445081617, + "p50": 24.645095419248985, + "p90": 27.57983248187916, + "p95": 28.13234306312641, + "p99": 32.24075360975402 + }, + "itl_ms": { + "mean": 23.811828228222925, + "p50": 16.618399997241795, + "p90": 24.79075759765692, + "p95": 53.653452219441554, + "p99": 184.00424657273106 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_64_4096_1024.jsonl" + }, + { + "name": "c1_i4096_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 65.20599544400466, + "request_throughput": 0.0766800654748646, + "input_token_throughput": 152.90005055688002, + "output_token_throughput": 86.29574568541263, + "total_token_throughput": 239.19579624229263, + "total_input_tokens": 9970, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 13039.41647579777, + "p50": 12737.218773021596, + "p90": 19326.684689195827, + "p95": 19438.629691599635, + "p99": 19528.185693522682 + }, + "ttft_ms": { + "mean": 107.96508298953995, + "p50": 105.82048198557459, + "p90": 120.15626538195647, + "p95": 122.30626518139616, + "p99": 124.0262650209479 + }, + "tpot_ms": { + "mean": 11.543713116983527, + "p50": 11.544842900470172, + "p90": 11.710704597846302, + "p95": 11.75094882191123, + "p99": 11.783144201163173 + }, + "itl_ms": { + "mean": 11.500716007827993, + "p50": 11.416781999287196, + "p90": 12.267208803677931, + "p95": 12.714743409014773, + "p99": 15.013036065502092 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_4096_2048.jsonl" + }, + { + "name": "c64_i4096_o2048", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 2048, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 117.00698560802266, + "request_throughput": 2.734879446189741, + "input_token_throughput": 5774.330451204056, + "output_token_throughput": 2846.0693886738927, + "total_token_throughput": 8620.39983987795, + "total_input_tokens": 675637, + "total_output_tokens": 333010, + "e2e_ms": { + "mean": 20535.820979047367, + "p50": 19770.545113497064, + "p90": 36951.179931193474, + "p95": 39745.30830668664, + "p99": 41227.42013381532 + }, + "ttft_ms": { + "mean": 297.6396630660929, + "p50": 127.86416050221305, + "p90": 920.5551686987747, + "p95": 1149.7123772627676, + "p99": 1194.8637982076616 + }, + "tpot_ms": { + "mean": 19.796835014518262, + "p50": 19.867121276273952, + "p90": 21.723155074566893, + "p95": 22.432242086481793, + "p99": 24.955436373794118 + }, + "itl_ms": { + "mean": 19.475918155825568, + "p50": 16.447670001070946, + "p90": 19.15072758274619, + "p95": 26.0455615032697, + "p99": 176.19469367782594 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_64_4096_2048.jsonl" + }, + { + "name": "c1_i4096_o4096", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 4096, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 137.51461238099728, + "request_throughput": 0.036359772342934915, + "input_token_throughput": 72.50138605181222, + "output_token_throughput": 85.59817604973738, + "total_token_throughput": 158.0995621015496, + "total_input_tokens": 9970, + "total_output_tokens": 11771, + "e2e_ms": { + "mean": 27500.528350204695, + "p50": 25900.430945999688, + "p90": 40624.2244923953, + "p95": 42270.912868197775, + "p99": 43588.26356883976 + }, + "ttft_ms": { + "mean": 114.71709080506116, + "p50": 113.29897999530658, + "p90": 127.63377840747125, + "p95": 130.4347272089217, + "p99": 132.67548625008203 + }, + "tpot_ms": { + "mean": 11.660428161282525, + "p50": 11.607732123008983, + "p90": 11.838800223548626, + "p95": 11.866398650268481, + "p99": 11.888477391644368 + }, + "itl_ms": { + "mean": 11.637672173722205, + "p50": 11.551771996892057, + "p90": 12.423009000485763, + "p95": 12.856199762609322, + "p99": 14.940864442905877 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_4096_4096.jsonl" + }, + { + "name": "c64_i4096_o4096", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 4096, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 214.53852150400053, + "request_throughput": 1.4915736239658617, + "input_token_throughput": 3149.2572767981965, + "output_token_throughput": 3050.9485914761212, + "total_token_throughput": 6200.205868274318, + "total_input_tokens": 675637, + "total_output_tokens": 654546, + "e2e_ms": { + "mean": 36687.187690068735, + "p50": 36015.92721400084, + "p90": 65686.69284979116, + "p95": 72324.60426831385, + "p99": 75036.71893385006 + }, + "ttft_ms": { + "mean": 274.7341550009878, + "p50": 121.60490201495122, + "p90": 876.4140803163173, + "p95": 900.9255425946321, + "p99": 999.7351078558131 + }, + "tpot_ms": { + "mean": 17.93428980380427, + "p50": 18.12657454228293, + "p90": 18.85609416246715, + "p95": 19.27635751648694, + "p99": 20.036325411799265 + }, + "itl_ms": { + "mean": 17.821273568422196, + "p50": 16.586008510785177, + "p90": 17.627767586964186, + "p95": 19.988030730746686, + "p99": 55.21536503219978 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_64_4096_4096.jsonl" + }, + { + "name": "c1_i16384_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 5.712559448002139, + "request_throughput": 0.8752644144033646, + "input_token_throughput": 7481.410108554199, + "output_token_throughput": 66.34504261177504, + "total_token_throughput": 7547.755151165974, + "total_input_tokens": 42738, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 1140.7567776041105, + "p50": 1153.5738079983275, + "p90": 1741.2836964067537, + "p95": 1856.5267082012724, + "p99": 1948.7211176368874 + }, + "ttft_ms": { + "mean": 320.95666300156154, + "p50": 255.25449600536376, + "p90": 575.1963478047401, + "p95": 599.0957394067663, + "p99": 618.2152526883874 + }, + "tpot_ms": { + "mean": 10.996233152215892, + "p50": 11.146897429644614, + "p90": 11.40574593279013, + "p95": 11.481190116210913, + "p99": 11.54154546294754 + }, + "itl_ms": { + "mean": 10.959262572126812, + "p50": 11.04035900789313, + "p90": 11.958558010519482, + "p95": 12.407819404324982, + "p99": 14.681235762254797 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_16384_128.jsonl" + }, + { + "name": "c32_i16384_o128", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 128, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 37.1104527740099, + "request_throughput": 4.311453729070509, + "input_token_throughput": 34791.24892014867, + "output_token_throughput": 284.71762563349375, + "total_token_throughput": 35075.96654578216, + "total_input_tokens": 1291119, + "total_output_tokens": 10566, + "e2e_ms": { + "mean": 7222.81702600103, + "p50": 6927.245188999223, + "p90": 12521.500642600584, + "p95": 13755.1466933437, + "p99": 15245.925571036641 + }, + "ttft_ms": { + "mean": 956.2753173306191, + "p50": 684.0546940075001, + "p90": 1860.2323261031415, + "p95": 3298.2727444323245, + "p99": 4051.797657485294 + }, + "tpot_ms": { + "mean": 107.20667041146244, + "p50": 102.95063398139787, + "p90": 146.80821743508776, + "p95": 186.59272597506057, + "p99": 376.91161463852035 + }, + "itl_ms": { + "mean": 96.37079262274476, + "p50": 15.931423506117426, + "p90": 315.78448468935676, + "p95": 334.5220921881269, + "p99": 419.7137621362343 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.38076923077, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_32_16384_128.jsonl" + }, + { + "name": "c1_i16384_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 7.071820794022642, + "request_throughput": 0.7070314909883152, + "input_token_throughput": 6043.422372371723, + "output_token_throughput": 71.69299318621516, + "total_token_throughput": 6115.115365557938, + "total_input_tokens": 42738, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1412.5724327983335, + "p50": 1449.3207980121952, + "p90": 2229.337644588668, + "p95": 2447.118662792491, + "p99": 2621.343477355549 + }, + "ttft_ms": { + "mean": 256.48318639723584, + "p50": 241.63091200171039, + "p90": 402.00019779149443, + "p95": 448.9649123861454, + "p99": 486.53668406186625 + }, + "tpot_ms": { + "mean": 11.51924006850755, + "p50": 11.537074755401687, + "p90": 11.659376842578114, + "p95": 11.662781071134695, + "p99": 11.665504453979961 + }, + "itl_ms": { + "mean": 11.53735575050547, + "p50": 11.457617016276345, + "p90": 12.345440016360953, + "p95": 13.56259299791418, + "p99": 14.976673992350698 + }, + "gpu_memory": { + "peak_used_mb": 139324.0, + "avg_used_mb": 139317.5, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_16384_256.jsonl" + }, + { + "name": "c32_i16384_o256", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 256, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 35.65484240101068, + "request_throughput": 4.487469000717406, + "input_token_throughput": 36211.603054607855, + "output_token_throughput": 623.0289773871028, + "total_token_throughput": 36834.63203199495, + "total_input_tokens": 1291119, + "total_output_tokens": 22214, + "e2e_ms": { + "mean": 6749.376519124962, + "p50": 6248.172036983306, + "p90": 11905.916951200925, + "p95": 12780.120356346015, + "p99": 13936.329891999774 + }, + "ttft_ms": { + "mean": 680.0791634877896, + "p50": 551.1939769930905, + "p90": 1328.4132753062295, + "p95": 1913.910021353506, + "p99": 2384.965779259219 + }, + "tpot_ms": { + "mean": 47.33705474009782, + "p50": 46.58911146607264, + "p90": 59.486993915876845, + "p95": 71.66590644790797, + "p99": 147.9650174480042 + }, + "itl_ms": { + "mean": 44.06801878353641, + "p50": 14.36969700444024, + "p90": 177.0988059870433, + "p95": 292.33303774526576, + "p99": 365.75512995623285 + }, + "gpu_memory": { + "peak_used_mb": 139684.0, + "avg_used_mb": 139370.66666666666, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_32_16384_256.jsonl" + }, + { + "name": "c1_i16384_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 6.524697318003746, + "request_throughput": 0.7663190729481636, + "input_token_throughput": 6550.188907931723, + "output_token_throughput": 77.7047539969438, + "total_token_throughput": 6627.893661928667, + "total_input_tokens": 42738, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1303.133088402683, + "p50": 1312.3146350262687, + "p90": 2065.8049791993108, + "p95": 2227.29969760403, + "p99": 2356.495472327806 + }, + "ttft_ms": { + "mean": 139.0515518025495, + "p50": 114.63064100826159, + "p90": 185.5096512066666, + "p95": 188.539885613136, + "p99": 190.9640731383115 + }, + "tpot_ms": { + "mean": 11.553020613458711, + "p50": 11.625021600048058, + "p90": 11.720145275427008, + "p95": 11.73107260839001, + "p99": 11.739814474760411 + }, + "itl_ms": { + "mean": 11.593969956117373, + "p50": 11.583370011067018, + "p90": 12.42344960628543, + "p95": 13.154048309661448, + "p99": 15.070866440946702 + }, + "gpu_memory": { + "peak_used_mb": 139684.0, + "avg_used_mb": 139408.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_16384_512.jsonl" + }, + { + "name": "c32_i16384_o512", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 512, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 42.4050869079947, + "request_throughput": 3.7731322269695653, + "input_token_throughput": 30447.26692345449, + "output_token_throughput": 952.4800665456296, + "total_token_throughput": 31399.746990000116, + "total_input_tokens": 1291119, + "total_output_tokens": 40390, + "e2e_ms": { + "mean": 7937.473418123591, + "p50": 7231.936971991672, + "p90": 14335.53286208771, + "p95": 16413.951087038724, + "p99": 18769.122077563075 + }, + "ttft_ms": { + "mean": 538.1829345238657, + "p50": 374.5491640002001, + "p90": 1393.5831179056543, + "p95": 1520.067489783105, + "p99": 2259.12406618183 + }, + "tpot_ms": { + "mean": 30.214154563376304, + "p50": 29.921590453918636, + "p90": 38.20460801400256, + "p95": 45.07352797602294, + "p99": 57.04345311538565 + }, + "itl_ms": { + "mean": 29.449055698720237, + "p50": 14.489118999335915, + "p90": 33.242931007407606, + "p95": 144.51645698864013, + "p99": 316.92803697660565 + }, + "gpu_memory": { + "peak_used_mb": 139684.0, + "avg_used_mb": 139408.4471830986, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_32_16384_512.jsonl" + }, + { + "name": "c1_i16384_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 18.25210122601129, + "request_throughput": 0.2739410623514645, + "input_token_throughput": 2341.5386245553777, + "output_token_throughput": 83.88075329201841, + "total_token_throughput": 2425.419377847396, + "total_input_tokens": 42738, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 3648.9271302009, + "p50": 1574.4030399946496, + "p90": 7676.770175999263, + "p95": 7809.608873003162, + "p99": 7915.879830606282 + }, + "ttft_ms": { + "mean": 188.47413159674034, + "p50": 166.91147000528872, + "p90": 289.86948799574753, + "p95": 322.9151319887023, + "p99": 349.35164718306623 + }, + "tpot_ms": { + "mean": 11.311722712704132, + "p50": 11.38147915044101, + "p90": 11.636269275296959, + "p95": 11.637638455246188, + "p99": 11.638733799205573 + }, + "itl_ms": { + "mean": 11.338147827002084, + "p50": 11.296455500996672, + "p90": 12.177108001196757, + "p95": 12.575102984555997, + "p99": 15.079722506925464 + }, + "gpu_memory": { + "peak_used_mb": 139684.0, + "avg_used_mb": 139409.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_16384_1024.jsonl" + }, + { + "name": "c32_i16384_o1024", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 1024, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 63.50027614500141, + "request_throughput": 2.519674081962159, + "input_token_throughput": 20332.49425643063, + "output_token_throughput": 1337.5374904835876, + "total_token_throughput": 21670.031746914217, + "total_input_tokens": 1291119, + "total_output_tokens": 84934, + "e2e_ms": { + "mean": 11657.908230049725, + "p50": 11766.50226500351, + "p90": 19649.950374499895, + "p95": 21919.155883429627, + "p99": 22977.80829768249 + }, + "ttft_ms": { + "mean": 485.63056064431294, + "p50": 246.81737599894404, + "p90": 1364.2390364984747, + "p95": 1871.965904346143, + "p99": 2404.3688034138167 + }, + "tpot_ms": { + "mean": 22.945847302867808, + "p50": 21.532263212585303, + "p90": 25.27922502447743, + "p95": 27.86078809842337, + "p99": 72.2763683168145 + }, + "itl_ms": { + "mean": 21.100112798235703, + "p50": 14.256738999392837, + "p90": 15.739107580156997, + "p95": 52.42427446501096, + "p99": 297.65237216226524 + }, + "gpu_memory": { + "peak_used_mb": 139684.0, + "avg_used_mb": 139409.41842105263, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_32_16384_1024.jsonl" + }, + { + "name": "c1_i16384_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 65.72091866700794, + "request_throughput": 0.07607927736576227, + "input_token_throughput": 650.2952312115896, + "output_token_throughput": 85.61961874742886, + "total_token_throughput": 735.9148499590184, + "total_input_tokens": 42738, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 13142.26782359765, + "p50": 12754.602688015439, + "p90": 19704.28160718293, + "p95": 19985.512879578164, + "p99": 20210.49789749435 + }, + "ttft_ms": { + "mean": 175.36014119395986, + "p50": 185.10537198744714, + "p90": 234.92859159014188, + "p95": 249.45631479495202, + "p99": 261.0784933588002 + }, + "tpot_ms": { + "mean": 11.542516854607184, + "p50": 11.560659686032267, + "p90": 11.633962648627595, + "p95": 11.641122501803924, + "p99": 11.646850384344985 + }, + "itl_ms": { + "mean": 11.532248108137457, + "p50": 11.443908995715901, + "p90": 12.273180313059129, + "p95": 12.68829941545846, + "p99": 14.829100963252131 + }, + "gpu_memory": { + "peak_used_mb": 139684.0, + "avg_used_mb": 139409.5, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_16384_2048.jsonl" + }, + { + "name": "c32_i16384_o2048", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 2048, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 102.62741485901643, + "request_throughput": 1.5590376140702626, + "input_token_throughput": 12580.644282754898, + "output_token_throughput": 1785.4683395437926, + "total_token_throughput": 14366.11262229869, + "total_input_tokens": 1291119, + "total_output_tokens": 183238, + "e2e_ms": { + "mean": 18450.049960798606, + "p50": 19650.882197995088, + "p90": 29807.86607058253, + "p95": 31359.527737388264, + "p99": 33430.94244295469 + }, + "ttft_ms": { + "mean": 336.451010986093, + "p50": 182.73530549777206, + "p90": 1068.0653378920397, + "p95": 1089.1261353419395, + "p99": 1111.2576313567115 + }, + "tpot_ms": { + "mean": 15.831536450525308, + "p50": 16.035249127389623, + "p90": 16.929491397301096, + "p95": 17.467017443684117, + "p99": 19.69697846989029 + }, + "itl_ms": { + "mean": 15.838644518932316, + "p50": 14.241769997170195, + "p90": 15.130802989006042, + "p95": 15.871898998739198, + "p99": 60.515860002488125 + }, + "gpu_memory": { + "peak_used_mb": 139684.0, + "avg_used_mb": 139479.6037037037, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_32_16384_2048.jsonl" + }, + { + "name": "c1_i65536_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 11.397514649986988, + "request_throughput": 0.43869213188558687, + "input_token_throughput": 15249.81588860677, + "output_token_throughput": 33.25286359692748, + "total_token_throughput": 15283.068752203697, + "total_input_tokens": 173810, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 2278.139853401808, + "p50": 2724.3857540015597, + "p90": 3841.2523665989283, + "p95": 4059.395702800248, + "p99": 4233.910371761303 + }, + "ttft_ms": { + "mean": 1429.4971552037168, + "p50": 1554.4339650077745, + "p90": 2710.1020148023963, + "p95": 2811.6455034061796, + "p99": 2892.880294289207 + }, + "tpot_ms": { + "mean": 11.473724474729648, + "p50": 11.380048349868352, + "p90": 11.930784581619424, + "p95": 12.084340916035751, + "p99": 12.207185983568813 + }, + "itl_ms": { + "mean": 11.68852257848584, + "p50": 11.67310102027841, + "p90": 12.547637592069805, + "p95": 13.033487010397947, + "p99": 15.609450997435488 + }, + "gpu_memory": { + "peak_used_mb": 139706.0, + "avg_used_mb": 139524.5, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_65536_128.jsonl" + }, + { + "name": "c8_i65536_o128", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 128, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 46.495504008024, + "request_throughput": 0.8602982342786728, + "input_token_throughput": 31649.769830348378, + "output_token_throughput": 55.231146640690795, + "total_token_throughput": 31705.000976989068, + "total_input_tokens": 1471572, + "total_output_tokens": 2568, + "e2e_ms": { + "mean": 9193.44558102457, + "p50": 8837.237635001657, + "p90": 17342.221115305438, + "p95": 17992.55950945808, + "p99": 18685.863364119432 + }, + "ttft_ms": { + "mean": 2642.309532523359, + "p50": 2382.497742000851, + "p90": 4619.818356982434, + "p95": 5855.872693145648, + "p99": 7061.538508331286 + }, + "tpot_ms": { + "mean": 115.3907831548218, + "p50": 107.64835458233807, + "p90": 174.2567664918026, + "p95": 327.7387829276752, + "p99": 399.9186071318399 + }, + "itl_ms": { + "mean": 107.2191137831152, + "p50": 11.844835506053641, + "p90": 351.82774128916213, + "p95": 420.32483855873573, + "p99": 448.0478705113637 + }, + "gpu_memory": { + "peak_used_mb": 139708.0, + "avg_used_mb": 139654.87837837837, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_8_65536_128.jsonl" + }, + { + "name": "c1_i65536_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 10.354734632011969, + "request_throughput": 0.48287089700419283, + "input_token_throughput": 16785.558121659753, + "output_token_throughput": 48.963108956225156, + "total_token_throughput": 16834.521230615977, + "total_input_tokens": 173810, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 2069.1889655892737, + "p50": 2424.590051989071, + "p90": 3329.392332781572, + "p95": 3540.820776380133, + "p99": 3709.9635312589817 + }, + "ttft_ms": { + "mean": 902.4706331896596, + "p50": 369.5778209948912, + "p90": 2014.7223625914194, + "p95": 2181.4932107925415, + "p99": 2314.909889353439 + }, + "tpot_ms": { + "mean": 11.550378226712771, + "p50": 11.603183148636614, + "p90": 11.927110441010495, + "p95": 11.945248954555396, + "p99": 11.959759765391317 + }, + "itl_ms": { + "mean": 11.880563763683936, + "p50": 11.901292018592358, + "p90": 12.793024972779676, + "p95": 13.358539014006965, + "p99": 15.600708706188017 + }, + "gpu_memory": { + "peak_used_mb": 139708.0, + "avg_used_mb": 139692.5, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_65536_256.jsonl" + }, + { + "name": "c8_i65536_o256", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 256, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 44.64320889499504, + "request_throughput": 0.895992940249517, + "input_token_throughput": 32962.953076721555, + "output_token_throughput": 117.73347234878653, + "total_token_throughput": 33080.68654907034, + "total_input_tokens": 1471572, + "total_output_tokens": 5256, + "e2e_ms": { + "mean": 8621.679103097995, + "p50": 7934.184520490817, + "p90": 15938.640361695434, + "p95": 16550.715314448462, + "p99": 18052.147336646158 + }, + "ttft_ms": { + "mean": 1800.3800100006629, + "p50": 1788.63854049996, + "p90": 3144.015901285457, + "p95": 4029.433374495418, + "p99": 4806.74102140154 + }, + "tpot_ms": { + "mean": 54.446565760702576, + "p50": 55.22089271177891, + "p90": 92.74740785803097, + "p95": 101.30015664374284, + "p99": 122.7065518255012 + }, + "itl_ms": { + "mean": 53.78479873170394, + "p50": 11.341089993948117, + "p90": 325.2451349981129, + "p95": 342.1970723953564, + "p99": 385.69993141572365 + }, + "gpu_memory": { + "peak_used_mb": 139708.0, + "avg_used_mb": 139694.57638888888, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_8_65536_256.jsonl" + }, + { + "name": "c1_i65536_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 8.023412760987412, + "request_throughput": 0.6231762155266044, + "input_token_throughput": 21662.851604135823, + "output_token_throughput": 63.19006825439769, + "total_token_throughput": 21726.04167239022, + "total_input_tokens": 173810, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1602.9774336027913, + "p50": 1639.2050010035746, + "p90": 2489.9309328000527, + "p95": 2564.6468784019817, + "p99": 2624.419634883525 + }, + "ttft_ms": { + "mean": 501.87500101164915, + "p50": 346.59205802017823, + "p90": 1054.3755090038758, + "p95": 1276.3666950049808, + "p99": 1453.959643805865 + }, + "tpot_ms": { + "mean": 11.056220900028002, + "p50": 11.125115478631763, + "p90": 11.556862828072946, + "p95": 11.680376113908292, + "p99": 11.77918674257657 + }, + "itl_ms": { + "mean": 11.189579554810756, + "p50": 11.18360050895717, + "p90": 12.12988500483334, + "p95": 12.547136211651376, + "p99": 14.437380578601728 + }, + "gpu_memory": { + "peak_used_mb": 139708.0, + "avg_used_mb": 139696.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_65536_512.jsonl" + }, + { + "name": "c8_i65536_o512", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 512, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 40.84438401600346, + "request_throughput": 0.9793268025373423, + "input_token_throughput": 36028.74753658705, + "output_token_throughput": 272.8404471869036, + "total_token_throughput": 36301.58798377395, + "total_input_tokens": 1471572, + "total_output_tokens": 11144, + "e2e_ms": { + "mean": 7629.467499878228, + "p50": 6605.449742506607, + "p90": 13734.331959995325, + "p95": 14481.515541051333, + "p99": 18250.23612089688 + }, + "ttft_ms": { + "mean": 1260.9102477501438, + "p50": 736.1879230156774, + "p90": 2563.182401913219, + "p95": 3168.1889003870274, + "p99": 5671.910491968155 + }, + "tpot_ms": { + "mean": 24.558571631178896, + "p50": 19.7090078711015, + "p90": 36.660957203864, + "p95": 51.5223379378131, + "p99": 85.55504920109868 + }, + "itl_ms": { + "mean": 23.329978548782595, + "p50": 11.118012014776468, + "p90": 12.710754189174624, + "p95": 23.5887666989584, + "p99": 342.11543018638616 + }, + "gpu_memory": { + "peak_used_mb": 139708.0, + "avg_used_mb": 139696.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_8_65536_512.jsonl" + }, + { + "name": "c1_i65536_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 18.417840418987907, + "request_throughput": 0.271475910652654, + "input_token_throughput": 9437.045606107557, + "output_token_throughput": 83.12592384184265, + "total_token_throughput": 9520.171529949399, + "total_input_tokens": 173810, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 3681.792501191376, + "p50": 1626.8658789922483, + "p90": 7768.170245189685, + "p95": 8015.790109592489, + "p99": 8213.886001114734 + }, + "ttft_ms": { + "mean": 255.57148939697072, + "p50": 295.48558199894615, + "p90": 365.17806919291615, + "p95": 375.57831059093587, + "p99": 383.89850370935164 + }, + "tpot_ms": { + "mean": 11.11591223133066, + "p50": 10.96062714980835, + "p90": 11.564500371784172, + "p95": 11.57499151231189, + "p99": 11.583384424734062 + }, + "itl_ms": { + "mean": 11.29259778707056, + "p50": 11.243843997363001, + "p90": 12.119136797264218, + "p95": 12.575050792656842, + "p99": 14.376279006246476 + }, + "gpu_memory": { + "peak_used_mb": 139708.0, + "avg_used_mb": 139696.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_65536_1024.jsonl" + }, + { + "name": "c8_i65536_o1024", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 1024, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 62.338421098014805, + "request_throughput": 0.6416588565358101, + "input_token_throughput": 23606.18017075288, + "output_token_throughput": 351.24405806770244, + "total_token_throughput": 23957.424228820582, + "total_input_tokens": 1471572, + "total_output_tokens": 21896, + "e2e_ms": { + "mean": 11157.950221427018, + "p50": 11160.75557350996, + "p90": 20058.121949192722, + "p95": 21105.82270954037, + "p99": 21507.370753068535 + }, + "ttft_ms": { + "mean": 962.3508537973976, + "p50": 418.21416800667066, + "p90": 2749.005644590943, + "p95": 2850.090325153724, + "p99": 2967.291713570012 + }, + "tpot_ms": { + "mean": 19.43057001452085, + "p50": 18.126048372799833, + "p90": 26.67870498145342, + "p95": 29.437979978438662, + "p99": 36.682113960456 + }, + "itl_ms": { + "mean": 18.854458797366757, + "p50": 11.316222997265868, + "p90": 12.648795178392902, + "p95": 13.506781545584087, + "p99": 334.8691878540558 + }, + "gpu_memory": { + "peak_used_mb": 139708.0, + "avg_used_mb": 139696.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_8_65536_1024.jsonl" + }, + { + "name": "c1_i131072_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 15.532598288002191, + "request_throughput": 0.32190364466337473, + "input_token_throughput": 23847.780849783587, + "output_token_throughput": 24.400296265483803, + "total_token_throughput": 23872.18114604907, + "total_input_tokens": 370418, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 3104.6353054058272, + "p50": 4526.820452010725, + "p90": 4888.86635240051, + "p95": 4990.354587201728, + "p99": 5071.545175042702 + }, + "ttft_ms": { + "mean": 2286.41628260375, + "p50": 3430.2771130169276, + "p90": 3812.3717041977216, + "p95": 3831.7083316040225, + "p99": 3847.1776335290633 + }, + "tpot_ms": { + "mean": 11.064339925313314, + "p50": 11.05356198367047, + "p90": 11.613551280170213, + "p95": 11.651908540225122, + "p99": 11.68259434826905 + }, + "itl_ms": { + "mean": 11.555975477430195, + "p50": 11.574425516300835, + "p90": 12.51095628249459, + "p95": 13.191249890951436, + "p99": 15.23967941524461 + }, + "gpu_memory": { + "peak_used_mb": 140228.0, + "avg_used_mb": 139805.56818181818, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_131072_128.jsonl" + }, + { + "name": "c4_i131072_o128", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 128, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 27.13875742800883, + "request_throughput": 0.7369534162739079, + "input_token_throughput": 54328.2426953833, + "output_token_throughput": 41.96949705679905, + "total_token_throughput": 54370.2121924401, + "total_input_tokens": 1474401, + "total_output_tokens": 1139, + "e2e_ms": { + "mean": 5273.325644248689, + "p50": 5078.873286503949, + "p90": 9009.436314093182, + "p95": 9530.159654750605, + "p99": 9800.838134941296 + }, + "ttft_ms": { + "mean": 2648.468313649937, + "p50": 2407.475689004059, + "p90": 5161.319839497446, + "p95": 5381.790485109378, + "p99": 6485.259353810396 + }, + "tpot_ms": { + "mean": 63.46264448269876, + "p50": 27.108041290587686, + "p90": 165.854421498146, + "p95": 234.23061024928757, + "p99": 254.36114444131087 + }, + "itl_ms": { + "mean": 49.66539044279866, + "p50": 11.527488008141518, + "p90": 63.46408920944667, + "p95": 397.0826292119454, + "p99": 499.1101731651 + }, + "gpu_memory": { + "peak_used_mb": 140228.0, + "avg_used_mb": 140084.00862068965, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_4_131072_128.jsonl" + }, + { + "name": "c1_i131072_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 10.823737689002883, + "request_throughput": 0.46194763247820503, + "input_token_throughput": 34222.74362546235, + "output_token_throughput": 46.84148993328999, + "total_token_throughput": 34269.58511539564, + "total_input_tokens": 370418, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 2162.711608601967, + "p50": 1606.9780830002856, + "p90": 3969.7245941963047, + "p95": 4514.326268597506, + "p99": 4950.007608118467 + }, + "ttft_ms": { + "mean": 1053.5080416011624, + "p50": 547.0652380026877, + "p90": 2534.259543009103, + "p95": 3143.29669700819, + "p99": 3630.5264202074613 + }, + "tpot_ms": { + "mean": 11.109271387096143, + "p50": 10.817969112548793, + "p90": 11.812963536160286, + "p95": 11.900103468407055, + "p99": 11.96981541420447 + }, + "itl_ms": { + "mean": 11.481921894436772, + "p50": 11.444862990174443, + "p90": 12.47322719427757, + "p95": 13.036605808883904, + "p99": 15.39386351883877 + }, + "gpu_memory": { + "peak_used_mb": 140228.0, + "avg_used_mb": 140216.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_131072_256.jsonl" + }, + { + "name": "c4_i131072_o256", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 256, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 39.31919323001057, + "request_throughput": 0.5086574356448113, + "input_token_throughput": 37498.25158860727, + "output_token_throughput": 64.77752442936672, + "total_token_throughput": 37563.02911303664, + "total_input_tokens": 1474401, + "total_output_tokens": 2547, + "e2e_ms": { + "mean": 7621.5941461516195, + "p50": 5433.910031002597, + "p90": 15992.410031994228, + "p95": 19293.47165230138, + "p99": 21326.096049646727 + }, + "ttft_ms": { + "mean": 2168.9784800997586, + "p50": 1628.2644945022184, + "p90": 4288.226667698473, + "p95": 4431.1157627482335, + "p99": 6485.733761349398 + }, + "tpot_ms": { + "mean": 38.017727809748095, + "p50": 26.924098604547815, + "p90": 76.59060437403086, + "p95": 82.59105530018105, + "p99": 93.3094082225064 + }, + "itl_ms": { + "mean": 45.02534406360306, + "p50": 11.698337984853424, + "p90": 62.21985211595896, + "p95": 360.9232887451071, + "p99": 418.3628251054324 + }, + "gpu_memory": { + "peak_used_mb": 140228.0, + "avg_used_mb": 140216.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_4_131072_256.jsonl" + }, + { + "name": "c1_i131072_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 7.443610455986345, + "request_throughput": 0.6717170423633426, + "input_token_throughput": 49763.21667962893, + "output_token_throughput": 68.11210809564294, + "total_token_throughput": 49831.328787724575, + "total_input_tokens": 370418, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1487.1138908027206, + "p50": 1618.9608690037858, + "p90": 2149.4011818023864, + "p95": 2243.5973944026046, + "p99": 2318.954364482779 + }, + "ttft_ms": { + "mean": 391.2680192035623, + "p50": 547.8159560007043, + "p90": 570.8218260144349, + "p95": 574.5017840177752, + "p99": 577.4457504204474 + }, + "tpot_ms": { + "mean": 10.888728879290689, + "p50": 10.649841338682782, + "p90": 11.532310937386393, + "p95": 11.536287318988197, + "p99": 11.539468424269643 + }, + "itl_ms": { + "mean": 11.320199055728514, + "p50": 11.297071498120204, + "p90": 12.151737086242065, + "p95": 12.580379500286654, + "p99": 15.034107333340218 + }, + "gpu_memory": { + "peak_used_mb": 140228.0, + "avg_used_mb": 140216.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_131072_512.jsonl" + }, + { + "name": "c4_i131072_o512", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 512, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 43.07605390899698, + "request_throughput": 0.464295082419858, + "input_token_throughput": 34227.856690746055, + "output_token_throughput": 136.38668046083328, + "total_token_throughput": 34364.24337120689, + "total_input_tokens": 1474401, + "total_output_tokens": 5875, + "e2e_ms": { + "mean": 8028.2892768489555, + "p50": 6942.520142998546, + "p90": 13616.571091485093, + "p95": 13969.639348344936, + "p99": 14391.104528077703 + }, + "ttft_ms": { + "mean": 1588.4933723005815, + "p50": 721.3263924932107, + "p90": 4283.278025590699, + "p95": 5162.584823240469, + "p99": 5751.134359843271 + }, + "tpot_ms": { + "mean": 24.25930484325447, + "p50": 21.142737899969127, + "p90": 43.33457116035198, + "p95": 43.94312149891555, + "p99": 51.734927765984985 + }, + "itl_ms": { + "mean": 22.61147524245899, + "p50": 11.681557996780612, + "p90": 13.17090202064719, + "p95": 17.04175149643561, + "p99": 376.24420104693854 + }, + "gpu_memory": { + "peak_used_mb": 140228.0, + "avg_used_mb": 140216.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_4_131072_512.jsonl" + }, + { + "name": "c1_i262144_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 262144, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 33.3968951869756, + "request_throughput": 0.14971451603530925, + "input_token_throughput": 22865.418947621467, + "output_token_throughput": 11.34836031547644, + "total_token_throughput": 22876.76730793694, + "total_input_tokens": 763634, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 6677.662302803947, + "p50": 6592.009656014852, + "p90": 12769.75543780718, + "p95": 14582.278500404207, + "p99": 16032.296950481832 + }, + "ttft_ms": { + "mean": 5896.153790998505, + "p50": 6455.220932024531, + "p90": 11764.465710002696, + "p95": 13444.272032997103, + "p99": 14788.117091392633 + }, + "tpot_ms": { + "mean": 9.882022091738845, + "p50": 10.501844686030772, + "p90": 11.01214369704212, + "p95": 11.086593334589374, + "p99": 11.146153044627178 + }, + "itl_ms": { + "mean": 11.628826648856853, + "p50": 11.615761992288753, + "p90": 12.903074515634216, + "p95": 14.062745511182584, + "p99": 16.517276962986216 + }, + "gpu_memory": { + "peak_used_mb": 140744.0, + "avg_used_mb": 140300.84016393442, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_262144_128.jsonl" + }, + { + "name": "c2_i262144_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 262144, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 36.61425120799686, + "request_throughput": 0.27311769789288814, + "input_token_throughput": 38069.90322105947, + "output_token_throughput": 20.64769796070234, + "total_token_throughput": 38090.55091902017, + "total_input_tokens": 1393901, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 6665.653762695729, + "p50": 7193.123516000924, + "p90": 10316.113390692044, + "p95": 10320.338272850495, + "p99": 10323.718178577255 + }, + "ttft_ms": { + "mean": 4480.795355394366, + "p50": 4243.354582009488, + "p90": 9116.933727281867, + "p95": 9292.653828128821, + "p99": 9433.229908806388 + }, + "tpot_ms": { + "mean": 24.302159523430515, + "p50": 10.971240596767418, + "p90": 72.93804791286638, + "p95": 74.40089603748876, + "p99": 75.57117453718669 + }, + "itl_ms": { + "mean": 32.082317728380346, + "p50": 11.63253202685155, + "p90": 14.834656001767144, + "p95": 24.26114000263624, + "p99": 520.8656103874092 + }, + "gpu_memory": { + "peak_used_mb": 140744.0, + "avg_used_mb": 140533.4631147541, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_2_262144_128.jsonl" + }, + { + "name": "c1_i262144_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 262144, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 27.865258064994123, + "request_throughput": 0.1794349073795687, + "input_token_throughput": 27404.519212377912, + "output_token_throughput": 18.194699608288264, + "total_token_throughput": 27422.7139119862, + "total_input_tokens": 763634, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 5571.334156603552, + "p50": 6127.82426000922, + "p90": 9963.428542204201, + "p95": 10356.68986660894, + "p99": 10671.298926132731 + }, + "ttft_ms": { + "mean": 4494.808082003146, + "p50": 4998.44012001995, + "p90": 8390.57087499532, + "p95": 8943.433845997788, + "p99": 9385.724222799763 + }, + "tpot_ms": { + "mean": 10.07351614397731, + "p50": 10.913098973415277, + "p90": 11.340758431304447, + "p95": 11.430213398637076, + "p99": 11.501777372503177 + }, + "itl_ms": { + "mean": 11.57473422585666, + "p50": 11.503823014209047, + "p90": 12.946098006796092, + "p95": 14.1087103926111, + "p99": 15.470532923936846 + }, + "gpu_memory": { + "peak_used_mb": 141258.0, + "avg_used_mb": 140712.5613207547, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_262144_256.jsonl" + }, + { + "name": "c2_i262144_o256", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 262144, + "output_len": 256, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 33.1799936350144, + "request_throughput": 0.30138643515130564, + "input_token_throughput": 42010.285334384, + "output_token_throughput": 42.07354634712227, + "total_token_throughput": 42052.358880731124, + "total_input_tokens": 1393901, + "total_output_tokens": 1396, + "e2e_ms": { + "mean": 6437.8450697957305, + "p50": 6647.003061501891, + "p90": 11981.908666883828, + "p95": 12049.746989947744, + "p99": 12104.017648398876 + }, + "ttft_ms": { + "mean": 2785.8514580962947, + "p50": 633.666234993143, + "p90": 7290.944269279133, + "p95": 9153.02144213783, + "p99": 10642.683180424794 + }, + "tpot_ms": { + "mean": 24.921164712144638, + "p50": 11.55330469214383, + "p90": 55.22409717675922, + "p95": 66.1042117439868, + "p99": 74.80830339776891 + }, + "itl_ms": { + "mean": 27.87743504576826, + "p50": 11.707381505402736, + "p90": 14.250949586858049, + "p95": 23.011322165257297, + "p99": 423.4108724640106 + }, + "gpu_memory": { + "peak_used_mb": 141258.0, + "avg_used_mb": 140860.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_2_262144_256.jsonl" + }, + { + "name": "c1_i524288_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 524288, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 38.84872146099224, + "request_throughput": 0.12870436431274757, + "input_token_throughput": 26404.421083200315, + "output_token_throughput": 9.755790814906266, + "total_token_throughput": 26414.176874015222, + "total_input_tokens": 1025778, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 7768.2642875937745, + "p50": 6653.598174976651, + "p90": 15560.610908200033, + "p95": 18082.004304596918, + "p99": 20099.119021714432 + }, + "ttft_ms": { + "mean": 7011.266513593728, + "p50": 6505.533494986594, + "p90": 14698.492897400867, + "p95": 17139.21816620277, + "p99": 19091.798381244298 + }, + "tpot_ms": { + "mean": 9.703946782833807, + "p50": 10.335227133570395, + "p90": 10.380124445705588, + "p95": 10.392965908855583, + "p99": 10.40323907937558 + }, + "itl_ms": { + "mean": 11.574165675833974, + "p50": 11.489819007692859, + "p90": 12.426574598066509, + "p95": 12.902599995140916, + "p99": 18.236666286247797 + }, + "gpu_memory": { + "peak_used_mb": 141258.0, + "avg_used_mb": 140860.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_524288_128.jsonl" + }, + { + "name": "c2_i524288_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 524288, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 14.471764257003088, + "request_throughput": 0.6910007530810116, + "input_token_throughput": 114432.8342136044, + "output_token_throughput": 52.239656932924476, + "total_token_throughput": 114485.07387053731, + "total_input_tokens": 1656045, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 2876.667488797102, + "p50": 1757.1999240026344, + "p90": 7034.463464684086, + "p95": 7604.526347841601, + "p99": 8060.576654367615 + }, + "ttft_ms": { + "mean": 1445.0251086003846, + "p50": 654.1992900019977, + "p90": 2486.3825416890886, + "p95": 4695.872217346909, + "p99": 6463.463957873174 + }, + "tpot_ms": { + "mean": 15.76570859944093, + "p50": 10.899829516808131, + "p90": 17.570392465287224, + "p95": 44.14282767919084, + "p99": 65.40077585031383 + }, + "itl_ms": { + "mean": 21.657978081799207, + "p50": 11.455839994596317, + "p90": 14.507261977996677, + "p95": 17.985764978220686, + "p99": 379.58602359867643 + }, + "gpu_memory": { + "peak_used_mb": 141258.0, + "avg_used_mb": 140860.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_2_524288_128.jsonl" + }, + { + "name": "c1_i1048576_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1048576, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 78.14055735501461, + "request_throughput": 0.06398725795214882, + "input_token_throughput": 19836.894596971106, + "output_token_throughput": 4.850234152772881, + "total_token_throughput": 19841.744831123877, + "total_input_tokens": 1550066, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 15626.558340591146, + "p50": 2301.4842919947114, + "p90": 40110.858696582734, + "p95": 46632.29924277984, + "p99": 51849.45167973754 + }, + "ttft_ms": { + "mean": 14906.361801398452, + "p50": 1038.3560300106183, + "p90": 39440.17306038296, + "p95": 46081.6615871794, + "p99": 51394.85240861657 + }, + "tpot_ms": { + "mean": 8.948563889984472, + "p50": 10.10617233331169, + "p90": 10.48167369132643, + "p95": 10.495872739994212, + "p99": 10.507231978928438 + }, + "itl_ms": { + "mean": 11.577846054635325, + "p50": 11.471398989669979, + "p90": 12.388931994792074, + "p95": 12.913330006995238, + "p99": 16.223136297776342 + }, + "gpu_memory": { + "peak_used_mb": 141258.0, + "avg_used_mb": 140860.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_1_1048576_128.jsonl" + }, + { + "name": "c2_i1048576_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 1048576, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 181.75334272100008, + "request_throughput": 0.055019620823978294, + "input_token_throughput": 17765.334885513093, + "output_token_throughput": 4.1594833342927595, + "total_token_throughput": 17769.494368847387, + "total_input_tokens": 3228909, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 30965.879701598897, + "p50": 32594.995560022653, + "p90": 58127.04405539552, + "p95": 62664.74741968849, + "p99": 66294.9101111229 + }, + "ttft_ms": { + "mean": 24258.31136170309, + "p50": 5467.431873519672, + "p90": 56506.835286997375, + "p95": 61414.69676498527, + "p99": 65340.9859473756 + }, + "tpot_ms": { + "mean": 117.0692356884987, + "p50": 11.282112643952987, + "p90": 461.9875949909769, + "p95": 500.4293399348777, + "p99": 531.1827358899984 + }, + "itl_ms": { + "mean": 106.13154969155116, + "p50": 11.54439800302498, + "p90": 458.76019130228065, + "p95": 734.37676950707, + "p99": 991.9316987271294 + }, + "gpu_memory": { + "peak_used_mb": 141780.0, + "avg_used_mb": 140941.92224880384, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/raw_outputs/vllm_main_2_1048576_128.jsonl" + } + ] +} \ No newline at end of file diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/scenarios.tsv b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/scenarios.tsv new file mode 100644 index 0000000..3717ac1 --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp2_dp4/scenarios.tsv @@ -0,0 +1,57 @@ +mark input_len output_len concurrency num_prompts +Y 1024 128 1 5 +Y 1024 128 128 640 +Y 1024 256 1 5 +Y 1024 256 128 640 +Y 1024 512 1 5 +Y 1024 512 128 640 +Y 1024 1024 1 5 +Y 1024 1024 128 640 +Y 1024 2048 1 5 +Y 1024 2048 128 640 +Y 1024 4096 1 5 +Y 1024 4096 128 640 +Y 4096 128 1 5 +Y 4096 128 64 320 +Y 4096 256 1 5 +Y 4096 256 64 320 +Y 4096 512 1 5 +Y 4096 512 64 320 +Y 4096 1024 1 5 +Y 4096 1024 64 320 +Y 4096 2048 1 5 +Y 4096 2048 64 320 +Y 4096 4096 1 5 +Y 4096 4096 64 320 +Y 16384 128 1 5 +Y 16384 128 32 160 +Y 16384 256 1 5 +Y 16384 256 32 160 +Y 16384 512 1 5 +Y 16384 512 32 160 +Y 16384 1024 1 5 +Y 16384 1024 32 160 +Y 16384 2048 1 5 +Y 16384 2048 32 160 +Y 65536 128 1 5 +Y 65536 128 8 40 +Y 65536 256 1 5 +Y 65536 256 8 40 +Y 65536 512 1 5 +Y 65536 512 8 40 +Y 65536 1024 1 5 +Y 65536 1024 8 40 +Y 131072 128 1 5 +Y 131072 128 4 20 +Y 131072 256 1 5 +Y 131072 256 4 20 +Y 131072 512 1 5 +Y 131072 512 4 20 +Y 262144 128 1 5 +Y 262144 128 2 10 +Y 262144 256 1 5 +Y 262144 256 2 10 +Y 524288 128 1 5 +Y 524288 128 2 10 +Y 1048576 128 1 5 +Y 1048576 128 2 10 diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/report.md b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/report.md new file mode 100644 index 0000000..7695093 --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/report.md @@ -0,0 +1,70 @@ +# 8x NVIDIA H200 143GB VLLM Benchmark Report + +- Result root: `/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2` +- Model: `/data/models/DeepSeek-V4-Flash` +- Backend: VLLM +- Benchmark client: `sglang.bench_serving --backend vllm` + +## Results + +| Scenario | Phase | Concurrency | Input | Output | Duration(s) | Success | Req/s | In tok/s | Out tok/s | Total tok/s | Mean TTFT(ms) | P95 TTFT(ms) | P99 TTFT(ms) | Mean TPOT(ms) | P95 TPOT(ms) | P99 TPOT(ms) | Mean E2E(ms) | P95 E2E(ms) | P99 E2E(ms) | Peak GPU mem | SLO | +|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| +| c1_i1024_o128 | main | 1 | 1024 | 128 | 3.72 | 5 | 1.34 | 477.80 | 101.85 | 579.65 | 134.63 | 302.85 | 345.83 | 8.17 | 8.32 | 8.35 | 742.89 | 1030.20 | 1055.00 | 138396/143771 MiB (96.3%) | ✅ | +| c128_i1024_o128 | main | 128 | 1024 | 128 | 42.00 | 640 | 15.24 | 7973.13 | 994.43 | 8967.56 | 615.83 | 1659.18 | 1917.69 | 122.83 | 156.63 | 189.20 | 8188.50 | 16737.02 | 18386.47 | 139454/143771 MiB (97.0%) | ⚠️ | +| c1_i1024_o256 | main | 1 | 1024 | 256 | 4.46 | 5 | 1.12 | 399.09 | 113.80 | 512.89 | 76.65 | 88.52 | 90.59 | 8.12 | 8.21 | 8.23 | 889.64 | 1486.72 | 1572.36 | 139454/143771 MiB (97.0%) | ✅ | +| c128_i1024_o256 | main | 128 | 1024 | 256 | 42.40 | 640 | 15.10 | 7897.93 | 1996.42 | 9894.36 | 381.79 | 938.43 | 1171.74 | 60.05 | 74.97 | 96.47 | 8045.59 | 15999.15 | 16952.04 | 139454/143771 MiB (97.0%) | ⚠️ | +| c1_i1024_o512 | main | 1 | 1024 | 512 | 4.58 | 5 | 1.09 | 388.12 | 110.67 | 498.80 | 101.05 | 187.00 | 208.64 | 8.12 | 8.17 | 8.18 | 914.85 | 1486.90 | 1572.17 | 139454/143771 MiB (97.0%) | ✅ | +| c128_i1024_o512 | main | 128 | 1024 | 512 | 54.32 | 640 | 11.78 | 6164.96 | 2986.46 | 9151.42 | 316.84 | 996.03 | 1011.18 | 39.13 | 48.34 | 56.02 | 10050.16 | 20325.81 | 22283.80 | 139456/143771 MiB (97.0%) | ✅ | +| c1_i1024_o1024 | main | 1 | 1024 | 1024 | 12.71 | 5 | 0.39 | 139.93 | 120.49 | 260.41 | 75.65 | 90.47 | 90.97 | 8.11 | 8.19 | 8.21 | 2539.90 | 5592.97 | 5705.34 | 139456/143771 MiB (97.0%) | ✅ | +| c128_i1024_o1024 | main | 128 | 1024 | 1024 | 74.21 | 640 | 8.62 | 4512.43 | 4359.31 | 8871.74 | 224.26 | 719.08 | 837.92 | 26.31 | 30.84 | 33.28 | 13282.76 | 25759.40 | 27367.26 | 139456/143771 MiB (97.0%) | ✅ | +| c1_i1024_o2048 | main | 1 | 1024 | 2048 | 45.78 | 5 | 0.11 | 38.84 | 122.91 | 161.75 | 77.63 | 84.75 | 84.77 | 8.08 | 8.09 | 8.09 | 9154.40 | 13865.78 | 13978.61 | 139456/143771 MiB (97.0%) | ✅ | +| c128_i1024_o2048 | main | 128 | 1024 | 2048 | 132.42 | 640 | 4.83 | 2528.71 | 4909.69 | 7438.40 | 249.17 | 979.55 | 1002.42 | 22.76 | 24.25 | 25.28 | 23085.59 | 43805.99 | 47303.18 | 139456/143771 MiB (97.0%) | ✅ | +| c1_i1024_o4096 | main | 1 | 1024 | 4096 | 95.72 | 5 | 0.05 | 18.57 | 122.97 | 141.55 | 77.88 | 82.10 | 82.14 | 8.09 | 8.12 | 8.13 | 19143.13 | 29602.89 | 30482.21 | 139456/143771 MiB (97.0%) | ✅ | +| c128_i1024_o4096 | main | 128 | 1024 | 4096 | 257.05 | 640 | 2.49 | 1302.66 | 5110.60 | 6413.26 | 197.57 | 737.03 | 754.71 | 21.93 | 23.01 | 23.26 | 44808.43 | 84504.69 | 90427.39 | 139456/143771 MiB (97.0%) | ✅ | +| c1_i4096_o128 | main | 1 | 4096 | 128 | 3.47 | 5 | 1.44 | 2872.58 | 109.20 | 2981.78 | 83.99 | 96.00 | 96.62 | 8.16 | 8.23 | 8.24 | 692.79 | 1028.22 | 1054.23 | 139456/143771 MiB (97.0%) | ✅ | +| c64_i4096_o128 | main | 64 | 4096 | 128 | 30.68 | 320 | 10.43 | 22020.97 | 682.69 | 22703.66 | 584.11 | 1904.20 | 2262.19 | 88.50 | 123.52 | 173.68 | 5949.69 | 11822.35 | 12463.74 | 139456/143771 MiB (97.0%) | ⚠️ | +| c1_i4096_o256 | main | 1 | 4096 | 256 | 4.51 | 5 | 1.11 | 2209.73 | 112.37 | 2322.10 | 83.55 | 91.50 | 91.90 | 8.16 | 8.23 | 8.24 | 900.98 | 1513.84 | 1604.71 | 139456/143771 MiB (97.0%) | ✅ | +| c64_i4096_o256 | main | 64 | 4096 | 256 | 31.29 | 320 | 10.23 | 21590.10 | 1323.77 | 22913.87 | 346.30 | 1198.05 | 1234.72 | 45.94 | 59.77 | 82.58 | 5923.11 | 11845.66 | 13085.09 | 139456/143771 MiB (97.0%) | ✅ | +| c1_i4096_o512 | main | 1 | 4096 | 512 | 4.55 | 5 | 1.10 | 2191.28 | 111.43 | 2302.71 | 91.00 | 104.51 | 107.11 | 8.16 | 8.24 | 8.25 | 908.65 | 1527.91 | 1621.06 | 139456/143771 MiB (97.0%) | ✅ | +| c64_i4096_o512 | main | 64 | 4096 | 512 | 39.52 | 320 | 8.10 | 17097.00 | 2143.08 | 19240.08 | 277.89 | 946.13 | 974.08 | 26.25 | 32.55 | 35.60 | 7228.62 | 14145.53 | 15173.06 | 139456/143771 MiB (97.0%) | ✅ | +| c1_i4096_o1024 | main | 1 | 4096 | 1024 | 12.82 | 5 | 0.39 | 777.58 | 119.41 | 896.98 | 82.49 | 92.40 | 93.46 | 8.15 | 8.23 | 8.24 | 2563.02 | 5648.98 | 5771.30 | 139456/143771 MiB (97.0%) | ✅ | +| c64_i4096_o1024 | main | 64 | 4096 | 1024 | 58.73 | 320 | 5.45 | 11503.60 | 2915.21 | 14418.81 | 261.52 | 1023.51 | 1212.54 | 19.18 | 21.78 | 24.49 | 10436.37 | 20083.65 | 21920.34 | 139824/143771 MiB (97.3%) | ✅ | +| c1_i4096_o2048 | main | 1 | 4096 | 2048 | 46.18 | 5 | 0.11 | 215.88 | 121.84 | 337.72 | 89.17 | 105.61 | 108.34 | 8.13 | 8.16 | 8.16 | 9235.07 | 14025.34 | 14152.06 | 139824/143771 MiB (97.3%) | ✅ | +| c64_i4096_o2048 | main | 64 | 4096 | 2048 | 105.18 | 320 | 3.04 | 6423.33 | 3165.95 | 9589.28 | 219.53 | 856.07 | 869.36 | 17.64 | 18.77 | 20.69 | 18415.93 | 35312.14 | 37188.62 | 139824/143771 MiB (97.3%) | ✅ | +| c1_i4096_o4096 | main | 1 | 4096 | 4096 | 96.28 | 5 | 0.05 | 103.55 | 122.26 | 225.82 | 92.47 | 110.67 | 114.17 | 8.14 | 8.17 | 8.17 | 19254.34 | 29794.95 | 30710.72 | 139824/143771 MiB (97.3%) | ✅ | +| c64_i4096_o4096 | main | 64 | 4096 | 4096 | 196.97 | 320 | 1.62 | 3430.14 | 3323.06 | 6753.20 | 191.83 | 727.11 | 753.66 | 16.53 | 17.22 | 17.64 | 33830.38 | 65711.11 | 68039.71 | 139824/143771 MiB (97.3%) | ✅ | +| c1_i16384_o128 | main | 1 | 16384 | 128 | 4.39 | 5 | 1.14 | 9724.92 | 86.24 | 9811.16 | 272.22 | 512.76 | 518.98 | 8.11 | 8.23 | 8.25 | 877.50 | 1371.53 | 1441.62 | 139824/143771 MiB (97.3%) | ✅ | +| c32_i16384_o128 | main | 32 | 16384 | 128 | 31.01 | 160 | 5.16 | 41639.17 | 340.76 | 41979.93 | 908.42 | 3479.51 | 3760.82 | 85.23 | 160.17 | 235.33 | 6030.16 | 11373.02 | 12999.09 | 139824/143771 MiB (97.3%) | ❌ | +| c1_i16384_o256 | main | 1 | 16384 | 256 | 5.10 | 5 | 0.98 | 8380.37 | 99.42 | 8479.79 | 203.25 | 407.06 | 440.10 | 8.14 | 8.23 | 8.24 | 1018.57 | 1804.68 | 1937.46 | 139824/143771 MiB (97.3%) | ✅ | +| c32_i16384_o256 | main | 32 | 16384 | 256 | 29.56 | 160 | 5.41 | 43677.33 | 751.48 | 44428.80 | 597.59 | 1701.48 | 2572.97 | 38.88 | 55.35 | 126.86 | 5607.62 | 10467.65 | 11645.26 | 140338/143771 MiB (97.6%) | ✅ | +| c1_i16384_o512 | main | 1 | 16384 | 512 | 4.66 | 5 | 1.07 | 9162.19 | 108.69 | 9270.88 | 114.10 | 155.92 | 157.11 | 8.16 | 8.23 | 8.25 | 931.42 | 1574.32 | 1661.52 | 140338/143771 MiB (97.6%) | ✅ | +| c32_i16384_o512 | main | 32 | 16384 | 512 | 29.42 | 160 | 5.44 | 43889.80 | 1373.00 | 45262.81 | 313.79 | 965.45 | 1010.01 | 20.31 | 25.61 | 28.12 | 5422.34 | 10895.57 | 12002.66 | 140854/143771 MiB (98.0%) | ✅ | +| c1_i16384_o1024 | main | 1 | 16384 | 1024 | 13.04 | 5 | 0.38 | 3277.50 | 117.41 | 3394.91 | 114.24 | 158.31 | 161.09 | 8.16 | 8.23 | 8.24 | 2606.54 | 5717.71 | 5837.98 | 140854/143771 MiB (98.0%) | ✅ | +| c32_i16384_o1024 | main | 32 | 16384 | 1024 | 49.82 | 160 | 3.21 | 25915.11 | 1704.78 | 27619.89 | 303.13 | 1131.20 | 1660.57 | 17.14 | 21.79 | 37.19 | 9072.32 | 16361.33 | 18824.49 | 140854/143771 MiB (98.0%) | ✅ | +| c1_i16384_o2048 | main | 1 | 16384 | 2048 | 46.44 | 5 | 0.11 | 920.20 | 121.16 | 1041.36 | 117.87 | 155.57 | 156.44 | 8.14 | 8.18 | 8.19 | 9287.27 | 14109.44 | 14233.84 | 140854/143771 MiB (98.0%) | ✅ | +| c32_i16384_o2048 | main | 32 | 16384 | 2048 | 92.42 | 160 | 1.73 | 13970.52 | 1982.72 | 15953.24 | 323.18 | 1143.92 | 2172.49 | 14.60 | 16.68 | 25.49 | 16690.84 | 28308.53 | 30322.94 | 140854/143771 MiB (98.0%) | ✅ | +| c1_i65536_o128 | main | 1 | 65536 | 128 | 8.91 | 5 | 0.56 | 19510.10 | 42.54 | 19552.65 | 1193.16 | 2211.56 | 2223.60 | 7.89 | 8.16 | 8.19 | 1780.28 | 3036.84 | 3092.42 | 140854/143771 MiB (98.0%) | ✅ | +| c8_i65536_o128 | main | 8 | 65536 | 128 | 42.45 | 40 | 0.94 | 34665.79 | 60.49 | 34726.28 | 2187.88 | 5620.08 | 5766.46 | 118.91 | 301.63 | 309.58 | 8428.69 | 16394.59 | 16549.56 | 140854/143771 MiB (98.0%) | ❌ | +| c1_i65536_o256 | main | 1 | 65536 | 256 | 4.96 | 5 | 1.01 | 35030.52 | 102.18 | 35132.70 | 190.89 | 274.65 | 283.52 | 7.97 | 8.23 | 8.25 | 990.97 | 1580.31 | 1647.86 | 140854/143771 MiB (98.0%) | ✅ | +| c8_i65536_o256 | main | 8 | 65536 | 256 | 30.60 | 40 | 1.31 | 48097.46 | 171.79 | 48269.25 | 1187.02 | 3353.05 | 4860.71 | 44.63 | 113.59 | 141.58 | 5938.64 | 14918.88 | 15303.64 | 140854/143771 MiB (98.0%) | ⚠️ | +| c1_i65536_o512 | main | 1 | 65536 | 512 | 5.10 | 5 | 0.98 | 34094.52 | 99.45 | 34193.97 | 221.62 | 326.62 | 330.25 | 7.91 | 8.17 | 8.18 | 1018.20 | 1589.95 | 1655.09 | 140854/143771 MiB (98.0%) | ✅ | +| c8_i65536_o512 | main | 8 | 65536 | 512 | 27.16 | 40 | 1.47 | 54172.15 | 410.24 | 54582.39 | 493.38 | 1809.22 | 2638.39 | 17.90 | 23.23 | 79.99 | 4993.77 | 8917.36 | 9676.38 | 140854/143771 MiB (98.0%) | ✅ | +| c1_i65536_o1024 | main | 1 | 65536 | 1024 | 13.63 | 5 | 0.37 | 12750.53 | 112.31 | 12862.85 | 229.69 | 358.50 | 364.11 | 8.07 | 8.26 | 8.26 | 2724.95 | 5751.59 | 5842.34 | 140854/143771 MiB (98.0%) | ✅ | +| c8_i65536_o1024 | main | 8 | 65536 | 1024 | 41.44 | 40 | 0.97 | 35510.70 | 528.38 | 36039.07 | 576.47 | 2177.55 | 2783.15 | 13.13 | 20.42 | 32.65 | 7344.83 | 12591.94 | 13878.42 | 140854/143771 MiB (98.0%) | ✅ | +| c1_i131072_o128 | main | 1 | 131072 | 128 | 13.24 | 5 | 0.38 | 27974.16 | 28.62 | 28002.78 | 2074.69 | 3498.43 | 3510.98 | 7.74 | 8.18 | 8.22 | 2646.89 | 4297.81 | 4353.06 | 141374/143771 MiB (98.3%) | ⚠️ | +| c4_i131072_o128 | main | 4 | 131072 | 128 | 32.85 | 20 | 0.61 | 44885.93 | 34.68 | 44920.61 | 2993.02 | 7688.92 | 7746.95 | 55.15 | 151.40 | 157.05 | 6305.32 | 12451.58 | 13546.32 | 141374/143771 MiB (98.3%) | ❌ | +| c1_i131072_o256 | main | 1 | 131072 | 256 | 8.19 | 5 | 0.61 | 45250.75 | 61.94 | 45312.69 | 851.06 | 2612.01 | 3033.01 | 7.81 | 8.23 | 8.24 | 1636.29 | 3468.17 | 3829.62 | 141374/143771 MiB (98.3%) | ✅ | +| c4_i131072_o256 | main | 4 | 131072 | 256 | 25.17 | 20 | 0.79 | 58583.41 | 101.20 | 58684.61 | 1578.82 | 6019.33 | 6092.09 | 20.62 | 43.90 | 46.90 | 4833.02 | 10204.22 | 10875.06 | 141374/143771 MiB (98.3%) | ⚠️ | +| c1_i131072_o512 | main | 1 | 131072 | 512 | 5.60 | 5 | 0.89 | 66152.93 | 90.55 | 66243.48 | 333.30 | 555.04 | 573.87 | 7.81 | 8.24 | 8.27 | 1118.43 | 1626.84 | 1649.69 | 141374/143771 MiB (98.3%) | ✅ | +| c4_i131072_o512 | main | 4 | 131072 | 512 | 19.45 | 20 | 1.03 | 75794.92 | 302.02 | 76096.94 | 489.33 | 724.28 | 1360.67 | 9.94 | 13.97 | 16.16 | 3412.52 | 5788.93 | 5861.60 | 141374/143771 MiB (98.3%) | ✅ | +| c1_i262144_o128 | main | 1 | 262144 | 128 | 24.68 | 5 | 0.20 | 30936.55 | 15.35 | 30951.90 | 4393.17 | 8221.07 | 8613.48 | 6.70 | 7.64 | 7.66 | 4935.30 | 9036.75 | 9509.11 | 141374/143771 MiB (98.3%) | ⚠️ | +| c2_i262144_o128 | main | 2 | 262144 | 128 | 30.76 | 10 | 0.33 | 45318.61 | 24.58 | 45343.19 | 3243.14 | 7994.94 | 8377.33 | 25.23 | 70.28 | 72.19 | 5572.85 | 9102.02 | 9106.67 | 141374/143771 MiB (98.3%) | ⚠️ | +| c1_i262144_o256 | main | 1 | 262144 | 256 | 7.02 | 5 | 0.71 | 108820.99 | 72.25 | 108893.24 | 643.55 | 962.12 | 1036.06 | 6.92 | 7.88 | 7.93 | 1401.77 | 2062.13 | 2080.08 | 141374/143771 MiB (98.3%) | ✅ | +| c2_i262144_o256 | main | 2 | 262144 | 256 | 20.99 | 10 | 0.48 | 66416.34 | 66.52 | 66482.86 | 1808.18 | 6399.54 | 6424.61 | 10.75 | 22.96 | 32.38 | 3491.75 | 7972.48 | 8063.51 | 141374/143771 MiB (98.3%) | ⚠️ | +| c1_i524288_o128 | main | 1 | 524288 | 128 | 23.69 | 5 | 0.21 | 43291.93 | 16.00 | 43307.93 | 4207.11 | 14806.51 | 17551.38 | 6.63 | 7.42 | 7.46 | 4736.94 | 15565.54 | 18281.61 | 141374/143771 MiB (98.3%) | ⚠️ | +| c2_i524288_o128 | main | 2 | 524288 | 128 | 15.61 | 10 | 0.64 | 106086.70 | 48.43 | 106135.13 | 1630.83 | 6241.67 | 9313.98 | 44.54 | 213.86 | 348.24 | 3078.79 | 10277.55 | 10806.98 | 141374/143771 MiB (98.3%) | ⚠️ | +| c1_i1048576_o128 | main | 1 | 1048576 | 128 | 77.70 | 5 | 0.06 | 19948.43 | 4.88 | 19953.31 | 15035.42 | 43228.08 | 48170.56 | 6.14 | 7.51 | 7.56 | 15539.21 | 43599.43 | 48471.96 | 141374/143771 MiB (98.3%) | ⚠️ | +| c2_i1048576_o128 | main | 2 | 1048576 | 128 | 165.96 | 10 | 0.06 | 19455.73 | 4.56 | 19460.29 | 19476.11 | 51577.89 | 52987.83 | 277.94 | 766.41 | 858.05 | 31427.72 | 55532.93 | 56546.05 | 141374/143771 MiB (98.3%) | ❌ | + +SLO: S2 tier — TTFT P95 < 3000ms, TPOT mean < 50ms. ✅ pass, ⚠️ partial, ❌ fail. + diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/results.json b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/results.json new file mode 100644 index 0000000..9bf2564 --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/results.json @@ -0,0 +1,3500 @@ +{ + "metadata": { + "experiment": "dsv4_h200_vllm_tp_dp_matrix_tp4_dp2", + "run_id": "20260709-152419_matrix", + "timestamp": "2026-07-09T16:42:56+00:00", + "model": "/data/models/DeepSeek-V4-Flash", + "backend": "vllm", + "engine": "vllm", + "hardware": "8x NVIDIA H200 143GB", + "accelerator": "NVIDIA H200", + "chip": "nvidia_h200", + "script": "experiments/dsv4_h200_vllm_tp_dp_matrix/run_bench.sh", + "env": "/data/user1/yy/envs/vllm", + "git_commit": "6fce89c", + "git_dirty": "dirty", + "description": "H200 vLLM TP×DP matrix for DeepSeek-V4-Flash" + }, + "config": { + "tp": 4, + "dp": 2, + "cuda_visible_devices": "0,1,2,3,4,5,6,7", + "backend": "vllm", + "server_start_script": "experiments/dsv4_h200_vllm_tp_dp_matrix/start_vllm_dp.sh", + "server_args": "vllm serve /data/models/DeepSeek-V4-Flash --trust-remote-code --kv-cache-dtype fp8 --block-size 256 --tensor-parallel-size 4 --no-enable-flashinfer-autotune --port 30030 --data-parallel-size 2 " + }, + "scenarios": [ + { + "name": "c1_i1024_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.721238563011866, + "request_throughput": 1.3436386609820414, + "input_token_throughput": 477.79790784521396, + "output_token_throughput": 101.84781050243875, + "total_token_throughput": 579.6457183476527, + "total_input_tokens": 1778, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 742.8900246100966, + "p50": 648.4752200194634, + "p90": 999.204512819415, + "p95": 1030.2014534187035, + "p99": 1054.9990058981346 + }, + "ttft_ms": { + "mean": 134.62597660836764, + "p50": 80.85439002024941, + "p90": 249.11989700049165, + "p95": 302.84766700351605, + "p99": 345.8298830059357 + }, + "tpot_ms": { + "mean": 8.170476576695364, + "p50": 8.114223049778957, + "p90": 8.283720724587985, + "p95": 8.321795637463547, + "p99": 8.352255567763997 + }, + "itl_ms": { + "mean": 8.13125441450673, + "p50": 8.066946495091543, + "p90": 8.375731605337931, + "p95": 8.54938578850124, + "p99": 10.11150098434882 + }, + "gpu_memory": { + "peak_used_mb": 138396.0, + "avg_used_mb": 138369.77777777778, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_1024_128.jsonl" + }, + { + "name": "c128_i1024_o128", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 128, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 41.99791230499977, + "request_throughput": 15.23885271611011, + "input_token_throughput": 7973.134416020392, + "output_token_throughput": 994.4303825556603, + "total_token_throughput": 8967.564798576053, + "total_input_tokens": 334855, + "total_output_tokens": 41764, + "e2e_ms": { + "mean": 8188.495863493518, + "p50": 7558.16386899096, + "p90": 15424.557712787648, + "p95": 16737.023079938077, + "p99": 18386.473187913944 + }, + "ttft_ms": { + "mean": 615.8316906878099, + "p50": 518.3006184961414, + "p90": 1314.747746993089, + "p95": 1659.175676117593, + "p99": 1917.6879239003756 + }, + "tpot_ms": { + "mean": 122.8253343572637, + "p50": 131.11594395073783, + "p90": 148.25015912092087, + "p95": 156.63260626495077, + "p99": 189.19791299325874 + }, + "itl_ms": { + "mean": 117.89939475868384, + "p50": 124.28834300953895, + "p90": 195.6383813987486, + "p95": 302.2298654948827, + "p99": 327.8783926862525 + }, + "gpu_memory": { + "peak_used_mb": 139454.0, + "avg_used_mb": 139059.94696969696, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_128_1024_128.jsonl" + }, + { + "name": "c1_i1024_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.455133901006775, + "request_throughput": 1.1223007234126219, + "input_token_throughput": 399.09013724552835, + "output_token_throughput": 113.80129335403987, + "total_token_throughput": 512.8914305995683, + "total_input_tokens": 1778, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 889.6417721989565, + "p50": 898.1078299984802, + "p90": 1379.6754283888733, + "p95": 1486.7199551837984, + "p99": 1572.3555766197387 + }, + "ttft_ms": { + "mean": 76.65484239696525, + "p50": 76.37333599268459, + "p90": 85.93957639532164, + "p95": 88.52160719688982, + "p99": 90.58723183814436 + }, + "tpot_ms": { + "mean": 8.124743332363352, + "p50": 8.102052595152728, + "p90": 8.18706675223157, + "p95": 8.209751876100608, + "p99": 8.227899975195841 + }, + "itl_ms": { + "mean": 8.097020840662832, + "p50": 8.049545009271242, + "p90": 8.32335549639538, + "p95": 8.41530616307864, + "p99": 8.954169903299773 + }, + "gpu_memory": { + "peak_used_mb": 139454.0, + "avg_used_mb": 139449.75, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_1024_256.jsonl" + }, + { + "name": "c128_i1024_o256", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 256, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 42.39779286499834, + "request_throughput": 15.095125400462875, + "input_token_throughput": 7897.934712456243, + "output_token_throughput": 1996.4246787449679, + "total_token_throughput": 9894.359391201211, + "total_input_tokens": 334855, + "total_output_tokens": 84644, + "e2e_ms": { + "mean": 8045.5932444916925, + "p50": 7782.692336491891, + "p90": 14681.59487861849, + "p95": 15999.15330719814, + "p99": 16952.04025982588 + }, + "ttft_ms": { + "mean": 381.79331519691004, + "p50": 277.9630430159159, + "p90": 912.2281327960081, + "p95": 938.4280478814617, + "p99": 1171.7404427187287 + }, + "tpot_ms": { + "mean": 60.04958801017436, + "p50": 61.515032658316734, + "p90": 71.85541459446462, + "p95": 74.96990560988317, + "p99": 96.47274696876381 + }, + "itl_ms": { + "mean": 58.417092998213164, + "p50": 24.514464515959844, + "p90": 176.99348521127834, + "p95": 184.3651863237028, + "p99": 194.41190875077154 + }, + "gpu_memory": { + "peak_used_mb": 139454.0, + "avg_used_mb": 139449.9514925373, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_128_1024_256.jsonl" + }, + { + "name": "c1_i1024_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.581034971983172, + "request_throughput": 1.0914564133605498, + "input_token_throughput": 388.1219005910115, + "output_token_throughput": 110.67368031475976, + "total_token_throughput": 498.7955809057713, + "total_input_tokens": 1778, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 914.846669806866, + "p50": 900.4292010213248, + "p90": 1380.3070137975737, + "p95": 1486.899900389835, + "p99": 1572.1742096636444 + }, + "ttft_ms": { + "mean": 101.05085760587826, + "p50": 74.2339999997057, + "p90": 159.94626079918817, + "p95": 186.99729139916596, + "p99": 208.63811587914824 + }, + "tpot_ms": { + "mean": 8.122948848832083, + "p50": 8.113513925797806, + "p90": 8.159414096796905, + "p95": 8.171356448323243, + "p99": 8.180910329544313 + }, + "itl_ms": { + "mean": 8.105077812727819, + "p50": 8.047397481277585, + "p90": 8.229623088845983, + "p95": 8.288775602704845, + "p99": 10.199027028575081 + }, + "gpu_memory": { + "peak_used_mb": 139454.0, + "avg_used_mb": 139450.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_1024_512.jsonl" + }, + { + "name": "c128_i1024_o512", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 512, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 54.31586038999376, + "request_throughput": 11.782930352289933, + "input_token_throughput": 6164.958036118821, + "output_token_throughput": 2986.4573411025854, + "total_token_throughput": 9151.415377221407, + "total_input_tokens": 334855, + "total_output_tokens": 162212, + "e2e_ms": { + "mean": 10050.157637585698, + "p50": 9373.689220505184, + "p90": 18887.582974819816, + "p95": 20325.81091970642, + "p99": 22283.797581810795 + }, + "ttft_ms": { + "mean": 316.84298680143, + "p50": 232.73386000073515, + "p90": 830.1055405085208, + "p95": 996.02754231164, + "p99": 1011.1826269913582 + }, + "tpot_ms": { + "mean": 39.128340454466525, + "p50": 40.164581184674624, + "p90": 46.59944953799815, + "p95": 48.344779400383295, + "p99": 56.0174129189656 + }, + "itl_ms": { + "mean": 38.57011740499057, + "p50": 22.13356748688966, + "p90": 63.24286598828621, + "p95": 172.91890101478202, + "p99": 190.09043615224076 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139450.90476190476, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_128_1024_512.jsonl" + }, + { + "name": "c1_i1024_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 12.706748941011028, + "request_throughput": 0.39349168093362585, + "input_token_throughput": 139.92564173999736, + "output_token_throughput": 120.48715270187624, + "total_token_throughput": 260.4127944418736, + "total_input_tokens": 1778, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 2539.89674160257, + "p50": 1058.6600590031594, + "p90": 5452.508239808958, + "p95": 5592.96783041209, + "p99": 5705.335502894595 + }, + "ttft_ms": { + "mean": 75.64942800672725, + "p50": 78.58753600157797, + "p90": 89.8377982142847, + "p95": 90.46904561109841, + "p99": 90.97404352854937 + }, + "tpot_ms": { + "mean": 8.111521713687166, + "p50": 8.099772917368442, + "p90": 8.170697841724433, + "p95": 8.190082070732515, + "p99": 8.20558945393898 + }, + "itl_ms": { + "mean": 8.074049801421676, + "p50": 8.056858496274799, + "p90": 8.245306002208963, + "p95": 8.300949004478753, + "p99": 8.51296549080871 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139451.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_1024_1024.jsonl" + }, + { + "name": "c128_i1024_o1024", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 1024, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 74.20719110002392, + "request_throughput": 8.62450108288486, + "input_token_throughput": 4512.433297045953, + "output_token_throughput": 4359.30797547592, + "total_token_throughput": 8871.741272521873, + "total_input_tokens": 334855, + "total_output_tokens": 323492, + "e2e_ms": { + "mean": 13282.760876018028, + "p50": 13183.164570495137, + "p90": 24293.26489258092, + "p95": 25759.395216204575, + "p99": 27367.25632587681 + }, + "ttft_ms": { + "mean": 224.26406962686087, + "p50": 111.3297620031517, + "p90": 671.5504883206451, + "p95": 719.0835456101921, + "p99": 837.91613197478 + }, + "tpot_ms": { + "mean": 26.30878799420686, + "p50": 26.38952824925881, + "p90": 28.918943739017084, + "p95": 30.83845577193247, + "p99": 33.282503663321584 + }, + "itl_ms": { + "mean": 25.89962998858941, + "p50": 21.29472600063309, + "p90": 43.20936339790933, + "p95": 46.90017320099287, + "p99": 103.21796319214592 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139451.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_128_1024_1024.jsonl" + }, + { + "name": "c1_i1024_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 45.78009264098364, + "request_throughput": 0.10921777811178691, + "input_token_throughput": 38.837841896551424, + "output_token_throughput": 122.91368748700499, + "total_token_throughput": 161.75152938355643, + "total_input_tokens": 1778, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 9154.397641000105, + "p50": 8897.216579993255, + "p90": 13724.741473596077, + "p95": 13865.781023795716, + "p99": 13978.612663955428 + }, + "ttft_ms": { + "mean": 77.6284478022717, + "p50": 79.23299202229828, + "p90": 84.720662800828, + "p95": 84.74754840717651, + "p99": 84.76905689225532 + }, + "tpot_ms": { + "mean": 8.076663309993533, + "p50": 8.075432795813127, + "p90": 8.087456426545188, + "p95": 8.091436403342898, + "p99": 8.094620384781065 + }, + "itl_ms": { + "mean": 8.072506932233855, + "p50": 8.059671483351849, + "p90": 8.231543694273569, + "p95": 8.282849067472853, + "p99": 8.382042522134725 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139451.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_1024_2048.jsonl" + }, + { + "name": "c128_i1024_o2048", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 2048, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 132.4214202449948, + "request_throughput": 4.833054945460686, + "input_token_throughput": 2528.707209003497, + "output_token_throughput": 4909.689072939647, + "total_token_throughput": 7438.3962819431445, + "total_input_tokens": 334855, + "total_output_tokens": 650148, + "e2e_ms": { + "mean": 23085.5917463311, + "p50": 22873.336221993668, + "p90": 40223.7335820857, + "p95": 43805.991935748876, + "p99": 47303.177158660554 + }, + "ttft_ms": { + "mean": 249.1724353542395, + "p50": 102.51995900762267, + "p90": 953.9042934979079, + "p95": 979.5460204622941, + "p99": 1002.4213002805482 + }, + "tpot_ms": { + "mean": 22.764648204889173, + "p50": 23.208953103962482, + "p90": 23.954017794092255, + "p95": 24.252731038794735, + "p99": 25.282301987327564 + }, + "itl_ms": { + "mean": 22.53238205072957, + "p50": 21.02372798253782, + "p90": 26.16267278790473, + "p95": 37.83958349958992, + "p99": 47.333332192502 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139451.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_128_1024_2048.jsonl" + }, + { + "name": "c1_i1024_o4096", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 4096, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 95.72129920398584, + "request_throughput": 0.05223497843823457, + "input_token_throughput": 18.57475833263621, + "output_token_throughput": 122.97158623929182, + "total_token_throughput": 141.54634457192805, + "total_input_tokens": 1778, + "total_output_tokens": 11771, + "e2e_ms": { + "mean": 19143.12961580581, + "p50": 17610.995654016733, + "p90": 28503.73940759455, + "p95": 29602.887815790014, + "p99": 30482.206542346394 + }, + "ttft_ms": { + "mean": 77.87798319477588, + "p50": 81.36516701779328, + "p90": 82.04711719299667, + "p95": 82.10042659775354, + "p99": 82.14307412155904 + }, + "tpot_ms": { + "mean": 8.092311643655734, + "p50": 8.081895106961245, + "p90": 8.123106116408039, + "p95": 8.124891838932284, + "p99": 8.12632041695168 + }, + "itl_ms": { + "mean": 8.101825746048762, + "p50": 8.096112505882047, + "p90": 8.268396501080133, + "p95": 8.321530003740918, + "p99": 8.465466307825409 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139451.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_1024_4096.jsonl" + }, + { + "name": "c128_i1024_o4096", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 4096, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 257.05401054699905, + "request_throughput": 2.489749133414062, + "input_token_throughput": 1302.663978233384, + "output_token_throughput": 5110.599119634458, + "total_token_throughput": 6413.263097867842, + "total_input_tokens": 334855, + "total_output_tokens": 1313700, + "e2e_ms": { + "mean": 44808.432847800716, + "p50": 45304.71561050217, + "p90": 78756.79078810208, + "p95": 84504.68779084622, + "p99": 90427.38911140477 + }, + "ttft_ms": { + "mean": 197.56539933837303, + "p50": 96.52409498812631, + "p90": 601.2236800772371, + "p95": 737.025586295931, + "p99": 754.7124139490188 + }, + "tpot_ms": { + "mean": 21.92814034068577, + "p50": 22.287282601925, + "p90": 22.78568289747275, + "p95": 23.0133071505868, + "p99": 23.259816896142823 + }, + "itl_ms": { + "mean": 21.750477804251904, + "p50": 20.887000500806607, + "p90": 22.717726315022446, + "p95": 26.77762978419194, + "p99": 44.002083983796176 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139452.15410958906, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_128_1024_4096.jsonl" + }, + { + "name": "c1_i4096_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.4707513700122945, + "request_throughput": 1.4406102503338603, + "input_token_throughput": 2872.5768391657175, + "output_token_throughput": 109.1982569753066, + "total_token_throughput": 2981.775096141024, + "total_input_tokens": 9970, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 692.7905376069248, + "p50": 674.2977160029113, + "p90": 995.7130086200777, + "p95": 1028.2247638213448, + "p99": 1054.2341679823585 + }, + "ttft_ms": { + "mean": 83.99056080379523, + "p50": 79.96891901711933, + "p90": 95.23673679796048, + "p95": 96.002811397193, + "p99": 96.61567107657902 + }, + "tpot_ms": { + "mean": 8.162352399671141, + "p50": 8.177870149665978, + "p90": 8.21795505574006, + "p95": 8.227887478063511, + "p99": 8.235833415922276 + }, + "itl_ms": { + "mean": 8.138307786181215, + "p50": 8.088838003459387, + "p90": 8.328236304805614, + "p95": 8.429230010369793, + "p99": 9.871305650740377 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139452.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_4096_128.jsonl" + }, + { + "name": "c64_i4096_o128", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 128, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 30.681525953987148, + "request_throughput": 10.429728967193535, + "input_token_throughput": 22020.97121939918, + "output_token_throughput": 682.6909467088618, + "total_token_throughput": 22703.662166108043, + "total_input_tokens": 675637, + "total_output_tokens": 20946, + "e2e_ms": { + "mean": 5949.694250859557, + "p50": 5584.752117501921, + "p90": 10855.172719899567, + "p95": 11822.347934574645, + "p99": 12463.743065452436 + }, + "ttft_ms": { + "mean": 584.1092637089787, + "p50": 435.9942669980228, + "p90": 1235.9103825932907, + "p95": 1904.1997952313977, + "p99": 2262.1926730405544 + }, + "tpot_ms": { + "mean": 88.50138026047055, + "p50": 89.95917342028015, + "p90": 108.05219886184639, + "p95": 123.51556064029701, + "p99": 173.68249789637068 + }, + "itl_ms": { + "mean": 83.2676578130938, + "p50": 21.50938200065866, + "p90": 192.7269242965849, + "p95": 199.1564502081019, + "p99": 313.02630993101155 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139452.80454545454, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_64_4096_128.jsonl" + }, + { + "name": "c1_i4096_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.511867786990479, + "request_throughput": 1.1081885010941592, + "input_token_throughput": 2209.7278711817535, + "output_token_throughput": 112.37031401094775, + "total_token_throughput": 2322.0981851927013, + "total_input_tokens": 9970, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 900.9787404036615, + "p50": 902.0479850005358, + "p90": 1400.2554600068836, + "p95": 1513.8433510030154, + "p99": 1604.713663799921 + }, + "ttft_ms": { + "mean": 83.55017400463112, + "p50": 81.13631498417817, + "p90": 90.98971001221798, + "p95": 91.49794401600957, + "p99": 91.90453121904284 + }, + "tpot_ms": { + "mean": 8.15765084948505, + "p50": 8.16715459563482, + "p90": 8.217339239593162, + "p95": 8.231538695014331, + "p99": 8.242898259351266 + }, + "itl_ms": { + "mean": 8.141259912392625, + "p50": 8.100810504402034, + "p90": 8.283181901788339, + "p95": 8.344838897755835, + "p99": 8.833542526408564 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139453.75, + "peak_utilization_pct": 98.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_4096_256.jsonl" + }, + { + "name": "c64_i4096_o256", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 256, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 31.293840416998137, + "request_throughput": 10.225654497368208, + "input_token_throughput": 21590.09539886989, + "output_token_throughput": 1323.7748850249232, + "total_token_throughput": 22913.870283894812, + "total_input_tokens": 675637, + "total_output_tokens": 41426, + "e2e_ms": { + "mean": 5923.105219631088, + "p50": 5607.908116013277, + "p90": 10917.56653348857, + "p95": 11845.662301342236, + "p99": 13085.091444506545 + }, + "ttft_ms": { + "mean": 346.30415208093837, + "p50": 259.8574580042623, + "p90": 865.4848864011001, + "p95": 1198.0460292965292, + "p99": 1234.7199589200318 + }, + "tpot_ms": { + "mean": 45.93971302723902, + "p50": 45.75125292484674, + "p90": 56.32194467989486, + "p95": 59.768785958604376, + "p99": 82.57894194812978 + }, + "itl_ms": { + "mean": 43.43177547151483, + "p50": 17.583779990673065, + "p90": 175.87184460135177, + "p95": 182.98797760508023, + "p99": 192.98271717270836 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139453.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_64_4096_256.jsonl" + }, + { + "name": "c1_i4096_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.549859455000842, + "request_throughput": 1.0989350439175434, + "input_token_throughput": 2191.2764775715814, + "output_token_throughput": 111.4320134532389, + "total_token_throughput": 2302.7084910248204, + "total_input_tokens": 9970, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 908.6494772054721, + "p50": 909.7984280087985, + "p90": 1411.4675548218656, + "p95": 1527.9056514205874, + "p99": 1621.0561286995653 + }, + "ttft_ms": { + "mean": 90.99595120642334, + "p50": 89.84892498119734, + "p90": 101.26915281289257, + "p95": 104.51462041819468, + "p99": 107.11099450243637 + }, + "tpot_ms": { + "mean": 8.15980729287909, + "p50": 8.17331734040326, + "p90": 8.221455233439666, + "p95": 8.236380992096548, + "p99": 8.248321599022052 + }, + "itl_ms": { + "mean": 8.143509780875393, + "p50": 8.110586990369484, + "p90": 8.28320438740775, + "p95": 8.370623656082898, + "p99": 9.090862147568261 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139453.75, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_4096_512.jsonl" + }, + { + "name": "c64_i4096_o512", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 512, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 39.517863471992314, + "request_throughput": 8.09760376410013, + "input_token_throughput": 17097.002232391624, + "output_token_throughput": 2143.081446192625, + "total_token_throughput": 19240.083678584248, + "total_input_tokens": 675637, + "total_output_tokens": 84690, + "e2e_ms": { + "mean": 7228.616324374616, + "p50": 6935.05255949276, + "p90": 13245.782141698875, + "p95": 14145.526426762808, + "p99": 15173.060689594131 + }, + "ttft_ms": { + "mean": 277.88907958192794, + "p50": 141.4275595016079, + "p90": 910.8460375049617, + "p95": 946.125633745396, + "p99": 974.0769699565135 + }, + "tpot_ms": { + "mean": 26.247129394423983, + "p50": 27.070249551602544, + "p90": 30.931282028845214, + "p95": 32.54885823472239, + "p99": 35.59856075350829 + }, + "itl_ms": { + "mean": 26.385256330396412, + "p50": 16.811637993669137, + "p90": 49.47247341624463, + "p95": 60.139739938313, + "p99": 180.50488640205 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139453.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_64_4096_512.jsonl" + }, + { + "name": "c1_i4096_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 12.82190531201195, + "request_throughput": 0.38995764500895574, + "input_token_throughput": 777.5755441478577, + "output_token_throughput": 119.40503090174225, + "total_token_throughput": 896.9805750496, + "total_input_tokens": 9970, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 2563.0167266062927, + "p50": 1058.7321980274282, + "p90": 5496.073938196059, + "p95": 5648.97837259341, + "p99": 5771.301920111291 + }, + "ttft_ms": { + "mean": 82.49331680126488, + "p50": 78.53085899841972, + "p90": 91.06979420175776, + "p95": 92.39708760287613, + "p99": 93.45892232377082 + }, + "tpot_ms": { + "mean": 8.151794980019885, + "p50": 8.163992704274799, + "p90": 8.211725569792538, + "p95": 8.225680909932814, + "p99": 8.236845182045036 + }, + "itl_ms": { + "mean": 8.127383405628319, + "p50": 8.122238999931142, + "p90": 8.349513504072092, + "p95": 8.392765994358342, + "p99": 8.53409474802902 + }, + "gpu_memory": { + "peak_used_mb": 139456.0, + "avg_used_mb": 139453.75, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_4096_1024.jsonl" + }, + { + "name": "c64_i4096_o1024", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 1024, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 58.73267454802408, + "request_throughput": 5.448415255435795, + "input_token_throughput": 11503.596681052732, + "output_token_throughput": 2915.2086350162685, + "total_token_throughput": 14418.805316069, + "total_input_tokens": 675637, + "total_output_tokens": 171218, + "e2e_ms": { + "mean": 10436.373365484087, + "p50": 10504.825365002034, + "p90": 18472.455321298912, + "p95": 20083.647405948435, + "p99": 21920.335104586557 + }, + "ttft_ms": { + "mean": 261.5205043149217, + "p50": 102.71516301145311, + "p90": 1005.7244442083175, + "p95": 1023.5087016786566, + "p99": 1212.53999641689 + }, + "tpot_ms": { + "mean": 19.178872612605836, + "p50": 19.110644546843904, + "p90": 21.463637178450764, + "p95": 21.78271678596347, + "p99": 24.485239472489173 + }, + "itl_ms": { + "mean": 19.0562145799521, + "p50": 16.3530970166903, + "p90": 20.924012403702374, + "p95": 34.67029542080124, + "p99": 63.48439392721067 + }, + "gpu_memory": { + "peak_used_mb": 139824.0, + "avg_used_mb": 139577.79494382022, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_64_4096_1024.jsonl" + }, + { + "name": "c1_i4096_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 46.18259557700367, + "request_throughput": 0.10826589405662852, + "input_token_throughput": 215.88219274891728, + "output_token_throughput": 121.84243717132973, + "total_token_throughput": 337.724629920247, + "total_input_tokens": 9970, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 9235.07033761125, + "p50": 9004.518708999967, + "p90": 13866.931839211611, + "p95": 14025.335175613873, + "p99": 14152.057844735682 + }, + "ttft_ms": { + "mean": 89.16751520009711, + "p50": 90.37135701510124, + "p90": 102.21057139569893, + "p95": 105.6140531960409, + "p99": 108.3368386363145 + }, + "tpot_ms": { + "mean": 8.12746096658243, + "p50": 8.122891957266937, + "p90": 8.162867814509612, + "p95": 8.163429550241974, + "p99": 8.163878938827862 + }, + "itl_ms": { + "mean": 8.133987881721893, + "p50": 8.125334992655553, + "p90": 8.319306685007177, + "p95": 8.373066302738152, + "p99": 8.47865227755392 + }, + "gpu_memory": { + "peak_used_mb": 139824.0, + "avg_used_mb": 139637.75, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_4096_2048.jsonl" + }, + { + "name": "c64_i4096_o2048", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 2048, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 105.18482336500892, + "request_throughput": 3.0422639860272094, + "input_token_throughput": 6423.331602273331, + "output_token_throughput": 3165.9510312091284, + "total_token_throughput": 9589.282633482459, + "total_input_tokens": 675637, + "total_output_tokens": 333010, + "e2e_ms": { + "mean": 18415.92838164952, + "p50": 17792.726314495667, + "p90": 32979.58519420354, + "p95": 35312.143221040606, + "p99": 37188.61529777787 + }, + "ttft_ms": { + "mean": 219.53445320232277, + "p50": 99.16603099554777, + "p90": 832.4278863117797, + "p95": 856.0696429529344, + "p99": 869.3559288178221 + }, + "tpot_ms": { + "mean": 17.642108510335945, + "p50": 17.896604079970523, + "p90": 18.40002850992256, + "p95": 18.76701874358469, + "p99": 20.691679305869712 + }, + "itl_ms": { + "mean": 17.513506270118697, + "p50": 15.979703981429338, + "p90": 17.643520201090723, + "p95": 23.456718999659657, + "p99": 50.41913705761543 + }, + "gpu_memory": { + "peak_used_mb": 139824.0, + "avg_used_mb": 139637.75, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_64_4096_2048.jsonl" + }, + { + "name": "c1_i4096_o4096", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 4096, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 96.27783238200936, + "request_throughput": 0.05193303459680204, + "input_token_throughput": 103.55447098602326, + "output_token_throughput": 122.26075004779136, + "total_token_throughput": 225.81522103381462, + "total_input_tokens": 9970, + "total_output_tokens": 11771, + "e2e_ms": { + "mean": 19254.338539595483, + "p50": 17712.654414004646, + "p90": 28650.246736989357, + "p95": 29794.95201698737, + "p99": 30710.716240985785 + }, + "ttft_ms": { + "mean": 92.46656260220334, + "p50": 92.35269099008292, + "p90": 106.2939728028141, + "p95": 110.66745939897372, + "p99": 114.16624867590144 + }, + "tpot_ms": { + "mean": 8.141002420165762, + "p50": 8.125413391334162, + "p90": 8.168172991052716, + "p95": 8.17006427269898, + "p99": 8.17157729801599 + }, + "itl_ms": { + "mean": 8.142885432604883, + "p50": 8.141148995491676, + "p90": 8.290865502203815, + "p95": 8.334165730047971, + "p99": 8.429930539568886 + }, + "gpu_memory": { + "peak_used_mb": 139824.0, + "avg_used_mb": 139637.75, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_4096_4096.jsonl" + }, + { + "name": "c64_i4096_o4096", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 4096, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 196.97081816900754, + "request_throughput": 1.6246061369630365, + "input_token_throughput": 3430.137551747797, + "output_token_throughput": 3323.0607766393987, + "total_token_throughput": 6753.198328387196, + "total_input_tokens": 675637, + "total_output_tokens": 654546, + "e2e_ms": { + "mean": 33830.37549459041, + "p50": 33209.42994249344, + "p90": 60112.03854111666, + "p95": 65711.10789460945, + "p99": 68039.70623786998 + }, + "ttft_ms": { + "mean": 191.82751641801588, + "p50": 96.30920199560933, + "p90": 569.6680827095406, + "p95": 727.1108964429004, + "p99": 753.6613261778257 + }, + "tpot_ms": { + "mean": 16.52614953470515, + "p50": 16.58643420264918, + "p90": 17.039129384364657, + "p95": 17.220080411641142, + "p99": 17.64209161867442 + }, + "itl_ms": { + "mean": 16.46906162684695, + "p50": 15.793798986123875, + "p90": 17.14870698051527, + "p95": 17.75683920131996, + "p99": 34.682686983142126 + }, + "gpu_memory": { + "peak_used_mb": 139824.0, + "avg_used_mb": 139637.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_64_4096_4096.jsonl" + }, + { + "name": "c1_i16384_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.39468751399545, + "request_throughput": 1.1377373212718433, + "input_token_throughput": 9724.923527303208, + "output_token_throughput": 86.24048895240573, + "total_token_throughput": 9811.164016255614, + "total_input_tokens": 42738, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 877.4986200034618, + "p50": 995.6299659970682, + "p90": 1283.916539006168, + "p95": 1371.532126003876, + "p99": 1441.624595602043 + }, + "ttft_ms": { + "mean": 272.21588700194843, + "p50": 189.40226899576373, + "p90": 504.99460959690623, + "p95": 512.7624117885716, + "p99": 518.9766535419039 + }, + "tpot_ms": { + "mean": 8.106169884019737, + "p50": 8.12891391548656, + "p90": 8.21255139165955, + "p95": 8.232200845685679, + "p99": 8.247920408906579 + }, + "itl_ms": { + "mean": 8.112757144796715, + "p50": 8.171425986802205, + "p90": 8.298453403403983, + "p95": 8.353496593190357, + "p99": 8.802264436380932 + }, + "gpu_memory": { + "peak_used_mb": 139824.0, + "avg_used_mb": 139637.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_16384_128.jsonl" + }, + { + "name": "c32_i16384_o128", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 128, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 31.007318050978938, + "request_throughput": 5.160072204146937, + "input_token_throughput": 41639.17040091244, + "output_token_throughput": 340.75826818135334, + "total_token_throughput": 41979.92866909379, + "total_input_tokens": 1291119, + "total_output_tokens": 10566, + "e2e_ms": { + "mean": 6030.158918974121, + "p50": 5963.966404495295, + "p90": 10334.437299703131, + "p95": 11373.024963619537, + "p99": 12999.094325524346 + }, + "ttft_ms": { + "mean": 908.4206920557335, + "p50": 687.4444764980581, + "p90": 2020.4356724978418, + "p95": 3479.511086911952, + "p99": 3760.819913863379 + }, + "tpot_ms": { + "mean": 85.23109945686367, + "p50": 82.87984177089432, + "p90": 122.94080610110656, + "p95": 160.16552974955013, + "p99": 235.3317044479384 + }, + "itl_ms": { + "mean": 79.13033230404655, + "p50": 14.328335513710044, + "p90": 287.1708374877926, + "p95": 316.8311752669979, + "p99": 376.5704659643234 + }, + "gpu_memory": { + "peak_used_mb": 139824.0, + "avg_used_mb": 139638.05, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_32_16384_128.jsonl" + }, + { + "name": "c1_i16384_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 5.09977360398625, + "request_throughput": 0.9804356797509085, + "input_token_throughput": 8380.372016238865, + "output_token_throughput": 99.41617792674212, + "total_token_throughput": 8479.788194165609, + "total_input_tokens": 42738, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1018.572311796015, + "p50": 1074.4801519904286, + "p90": 1638.7087909970433, + "p95": 1804.6806729980742, + "p99": 1937.4581785988994 + }, + "ttft_ms": { + "mean": 203.24994219699875, + "p50": 159.71414401428774, + "p90": 365.7567747926805, + "p95": 407.05845238990145, + "p99": 440.0997944676783 + }, + "tpot_ms": { + "mean": 8.143973614199677, + "p50": 8.109469493050915, + "p90": 8.210399791161192, + "p95": 8.226191845765866, + "p99": 8.238825489449606 + }, + "itl_ms": { + "mean": 8.13648705786659, + "p50": 8.161870995536447, + "p90": 8.321528002852574, + "p95": 8.370989991817623, + "p99": 8.841439994284883 + }, + "gpu_memory": { + "peak_used_mb": 139824.0, + "avg_used_mb": 139639.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_16384_256.jsonl" + }, + { + "name": "c32_i16384_o256", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 256, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 29.56039488798706, + "request_throughput": 5.412647584928638, + "input_token_throughput": 43677.32585753423, + "output_token_throughput": 751.4784590725297, + "total_token_throughput": 44428.804316606765, + "total_input_tokens": 1291119, + "total_output_tokens": 22214, + "e2e_ms": { + "mean": 5607.618775876108, + "p50": 5105.33775499789, + "p90": 9879.301131807733, + "p95": 10467.650522004986, + "p99": 11645.257351046312 + }, + "ttft_ms": { + "mean": 597.5871927063054, + "p50": 437.5608239934081, + "p90": 1639.2458354792325, + "p95": 1701.4821891032575, + "p99": 2572.9686887274147 + }, + "tpot_ms": { + "mean": 38.882393224988, + "p50": 38.051979200099595, + "p90": 49.37223125852247, + "p95": 55.3454732937098, + "p99": 126.85517602935364 + }, + "itl_ms": { + "mean": 36.51273482805573, + "p50": 13.292896983330138, + "p90": 76.30884070240428, + "p95": 260.71366565447534, + "p99": 291.7771289261873 + }, + "gpu_memory": { + "peak_used_mb": 140338.0, + "avg_used_mb": 139886.85185185185, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_32_16384_256.jsonl" + }, + { + "name": "c1_i16384_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.664603701996384, + "request_throughput": 1.0719024207479986, + "input_token_throughput": 9162.193131585593, + "output_token_throughput": 108.69090546384706, + "total_token_throughput": 9270.88403704944, + "total_input_tokens": 42738, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 931.4195751969237, + "p50": 938.0052679916844, + "p90": 1465.3151820064522, + "p95": 1574.3161850026809, + "p99": 1661.5169873996638 + }, + "ttft_ms": { + "mean": 114.09855700330809, + "p50": 106.6119369934313, + "p90": 154.4245808152482, + "p95": 155.91656641336158, + "p99": 157.1101548918523 + }, + "tpot_ms": { + "mean": 8.155400557707189, + "p50": 8.150915009786795, + "p90": 8.213660326579516, + "p95": 8.232808513492545, + "p99": 8.248127063022967 + }, + "itl_ms": { + "mean": 8.14015101784037, + "p50": 8.16920849320013, + "p90": 8.31848010129761, + "p95": 8.359751298849005, + "p99": 8.989940869214479 + }, + "gpu_memory": { + "peak_used_mb": 140338.0, + "avg_used_mb": 140085.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_16384_512.jsonl" + }, + { + "name": "c32_i16384_o512", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 512, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 29.41728782298742, + "request_throughput": 5.438978636058078, + "input_token_throughput": 43889.80411005418, + "output_token_throughput": 1373.0021694399109, + "total_token_throughput": 45262.80627949409, + "total_input_tokens": 1291119, + "total_output_tokens": 40390, + "e2e_ms": { + "mean": 5422.335548431511, + "p50": 4861.034579997067, + "p90": 9935.616184407263, + "p95": 10895.570411083463, + "p99": 12002.661855036857 + }, + "ttft_ms": { + "mean": 313.7887812115878, + "p50": 185.7860879972577, + "p90": 717.2196262981743, + "p95": 965.4450014510074, + "p99": 1010.0096490039141 + }, + "tpot_ms": { + "mean": 20.31214420877035, + "p50": 20.513349666405176, + "p90": 24.077787990479806, + "p95": 25.607989078959847, + "p99": 28.121488541834363 + }, + "itl_ms": { + "mean": 20.385150807390108, + "p50": 12.747994507662952, + "p90": 22.309271997073665, + "p95": 54.75893750553951, + "p99": 216.78622414765437 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140231.28773584904, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_32_16384_512.jsonl" + }, + { + "name": "c1_i16384_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 13.03982701501809, + "request_throughput": 0.38344066943844063, + "input_token_throughput": 3277.497466092015, + "output_token_throughput": 117.40953298205052, + "total_token_throughput": 3394.906999074066, + "total_input_tokens": 42738, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 2606.541334395297, + "p50": 1140.9922299790196, + "p90": 5567.364295793232, + "p95": 5717.706294392701, + "p99": 5837.979893272277 + }, + "ttft_ms": { + "mean": 114.23504619742744, + "p50": 99.76904699578881, + "p90": 154.83683619531803, + "p95": 158.30918259453028, + "p99": 161.0870597139001 + }, + "tpot_ms": { + "mean": 8.162550573447826, + "p50": 8.17030822964012, + "p90": 8.216208814917731, + "p95": 8.229407707511978, + "p99": 8.239966821587378 + }, + "itl_ms": { + "mean": 8.165951017700783, + "p50": 8.172732996172272, + "p90": 8.311030003824271, + "p95": 8.360464998986572, + "p99": 8.46713301143609 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_16384_1024.jsonl" + }, + { + "name": "c32_i16384_o1024", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 1024, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 49.821092842001235, + "request_throughput": 3.2114911751817976, + "input_token_throughput": 25915.10796630967, + "output_token_throughput": 1704.7799467055677, + "total_token_throughput": 27619.887913015238, + "total_input_tokens": 1291119, + "total_output_tokens": 84934, + "e2e_ms": { + "mean": 9072.324467187173, + "p50": 9554.756495999754, + "p90": 15422.759670595404, + "p95": 16361.328559013782, + "p99": 18824.492606802087 + }, + "ttft_ms": { + "mean": 303.1298276508096, + "p50": 150.8763884921791, + "p90": 752.9843283031369, + "p95": 1131.2044626596617, + "p99": 1660.5693382397294 + }, + "tpot_ms": { + "mean": 17.136457382381813, + "p50": 16.412214171525452, + "p90": 19.556467973074525, + "p95": 21.79351695247337, + "p99": 37.19118919999149 + }, + "itl_ms": { + "mean": 16.573541087823227, + "p50": 13.859958009561524, + "p90": 15.146375395124782, + "p95": 22.501056210603558, + "p99": 107.31219191686252 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_32_16384_1024.jsonl" + }, + { + "name": "c1_i16384_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 46.44400656002108, + "request_throughput": 0.1076565173923645, + "input_token_throughput": 920.2048480629747, + "output_token_throughput": 121.156644673367, + "total_token_throughput": 1041.3614927363417, + "total_input_tokens": 42738, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 9287.265716999536, + "p50": 9034.327834990108, + "p90": 13953.932464198442, + "p95": 14109.439255605685, + "p99": 14233.844688731479 + }, + "ttft_ms": { + "mean": 117.8685202030465, + "p50": 106.28899198491126, + "p90": 154.4862876064144, + "p95": 155.56900080409832, + "p99": 156.43517136224546 + }, + "tpot_ms": { + "mean": 8.139814384597937, + "p50": 8.16596810866496, + "p90": 8.179636834119448, + "p95": 8.183121171989992, + "p99": 8.185908642286426 + }, + "itl_ms": { + "mean": 8.15487424369235, + "p50": 8.157402990036644, + "p90": 8.296986200730316, + "p95": 8.341667961212806, + "p99": 8.466342803440057 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_16384_2048.jsonl" + }, + { + "name": "c32_i16384_o2048", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 2048, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 92.41738028498366, + "request_throughput": 1.731276081475309, + "input_token_throughput": 13970.521518989497, + "output_token_throughput": 1982.7222913585792, + "total_token_throughput": 15953.243810348076, + "total_input_tokens": 1291119, + "total_output_tokens": 183238, + "e2e_ms": { + "mean": 16690.838252105823, + "p50": 17538.859395004692, + "p90": 26505.350084725065, + "p95": 28308.53404565277, + "p99": 30322.94307942211 + }, + "ttft_ms": { + "mean": 323.1806549762041, + "p50": 138.71007499983534, + "p90": 1080.8269529923562, + "p95": 1143.9156597625697, + "p99": 2172.491064503556 + }, + "tpot_ms": { + "mean": 14.598591226013406, + "p50": 14.4070574506273, + "p90": 16.022179939151584, + "p95": 16.681686655123066, + "p99": 25.48573569263988 + }, + "itl_ms": { + "mean": 14.31456483647756, + "p50": 12.639326494536363, + "p90": 14.497518795542419, + "p95": 14.90802480402635, + "p99": 51.936214853776605 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_32_16384_2048.jsonl" + }, + { + "name": "c1_i65536_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 8.908717874990543, + "request_throughput": 0.5612479899084589, + "input_token_throughput": 19510.102625197847, + "output_token_throughput": 42.542597635061185, + "total_token_throughput": 19552.64522283291, + "total_input_tokens": 173810, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 1780.2822354016826, + "p50": 2178.572840988636, + "p90": 2967.3524308018386, + "p95": 3036.8367914052214, + "p99": 3092.4242798879277 + }, + "ttft_ms": { + "mean": 1193.1577254086733, + "p50": 1373.9548500161618, + "p90": 2196.5134602040052, + "p95": 2211.5634405985475, + "p99": 2223.6034249141812 + }, + "tpot_ms": { + "mean": 7.894534837551642, + "p50": 7.892211842877898, + "p90": 8.117741047074862, + "p95": 8.158157373933742, + "p99": 8.190490435420847 + }, + "itl_ms": { + "mean": 8.176474356446624, + "p50": 8.269965008366853, + "p90": 8.471901004668325, + "p95": 8.5723778931424, + "p99": 10.3457129985327 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_65536_128.jsonl" + }, + { + "name": "c8_i65536_o128", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 128, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 42.45026601900463, + "request_throughput": 0.942279136297811, + "input_token_throughput": 34665.789829001056, + "output_token_throughput": 60.49432055031947, + "total_token_throughput": 34726.28414955138, + "total_input_tokens": 1471572, + "total_output_tokens": 2568, + "e2e_ms": { + "mean": 8428.691745326068, + "p50": 8212.495325497002, + "p90": 14741.123111880735, + "p95": 16394.59441000945, + "p99": 16549.55801117263 + }, + "ttft_ms": { + "mean": 2187.8825422718364, + "p50": 2190.3561929939315, + "p90": 3844.8033021006268, + "p95": 5620.080803416204, + "p99": 5766.461412440112 + }, + "tpot_ms": { + "mean": 118.90660609446272, + "p50": 113.07719088074825, + "p90": 202.0349033401, + "p95": 301.6251983424202, + "p99": 309.5849867507786 + }, + "itl_ms": { + "mean": 102.34973051988773, + "p50": 9.896511008264497, + "p90": 317.9538198048249, + "p95": 329.674046713626, + "p99": 393.747671394958 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_8_65536_128.jsonl" + }, + { + "name": "c1_i65536_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.961673725018045, + "request_throughput": 1.007724464990252, + "input_token_throughput": 35030.51785199114, + "output_token_throughput": 102.18326075001156, + "total_token_throughput": 35132.70111274115, + "total_input_tokens": 173810, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 990.9721931966487, + "p50": 1040.3953449858818, + "p90": 1495.8696421876086, + "p95": 1580.3088365821168, + "p99": 1647.8601920977235 + }, + "ttft_ms": { + "mean": 190.88517780182883, + "p50": 220.14280201983638, + "p90": 263.5703456006013, + "p95": 274.6538198029156, + "p99": 283.5205991647672 + }, + "tpot_ms": { + "mean": 7.969151561029765, + "p50": 7.941915901884547, + "p90": 8.202125436961998, + "p95": 8.227581068430037, + "p99": 8.247945573604467 + }, + "itl_ms": { + "mean": 8.180374910022705, + "p50": 8.235591987613589, + "p90": 8.446013601496816, + "p95": 8.517567615490407, + "p99": 9.299252630444247 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_65536_256.jsonl" + }, + { + "name": "c8_i65536_o256", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 256, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 30.595628153998405, + "request_throughput": 1.307376328365155, + "input_token_throughput": 48097.4599571242, + "output_token_throughput": 171.78924954718136, + "total_token_throughput": 48269.24920667138, + "total_input_tokens": 1471572, + "total_output_tokens": 5256, + "e2e_ms": { + "mean": 5938.643281003169, + "p50": 5732.69273652113, + "p90": 10639.590408897493, + "p95": 14918.883552541956, + "p99": 15303.637388587522 + }, + "ttft_ms": { + "mean": 1187.0219872776943, + "p50": 467.0099939976353, + "p90": 3200.386212713784, + "p95": 3353.049842607287, + "p99": 4860.708494472781 + }, + "tpot_ms": { + "mean": 44.63412787993672, + "p50": 33.272964906794506, + "p90": 100.21680506677325, + "p95": 113.58755296002045, + "p99": 141.58472553635613 + }, + "itl_ms": { + "mean": 38.50554212176001, + "p50": 9.629958993173204, + "p90": 63.88599150523078, + "p95": 306.93651526235044, + "p99": 331.01125874964055 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_8_65536_256.jsonl" + }, + { + "name": "c1_i65536_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 5.097886697010836, + "request_throughput": 0.9807985734425538, + "input_token_throughput": 34094.520010010056, + "output_token_throughput": 99.45297534707495, + "total_token_throughput": 34193.972985357126, + "total_input_tokens": 173810, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1018.1994763959665, + "p50": 1056.3833659980446, + "p90": 1508.5126165882684, + "p95": 1589.9459927866699, + "p99": 1655.0926937453914 + }, + "ttft_ms": { + "mean": 221.62047139718197, + "p50": 248.06780202197842, + "p90": 322.0881185901817, + "p95": 326.62323578842916, + "p99": 330.2513295470271 + }, + "tpot_ms": { + "mean": 7.9134865962759235, + "p50": 7.924662391922218, + "p90": 8.159459676510565, + "p95": 8.17162573889289, + "p99": 8.181358588798755 + }, + "itl_ms": { + "mean": 8.161189641348338, + "p50": 8.249466991401277, + "p90": 8.46966979734134, + "p95": 8.586531548644416, + "p99": 9.508340466709342 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_65536_512.jsonl" + }, + { + "name": "c8_i65536_o512", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 512, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 27.16473425901495, + "request_throughput": 1.472497379087208, + "input_token_throughput": 54172.14782845302, + "output_token_throughput": 410.2377698136961, + "total_token_throughput": 54582.385598266716, + "total_input_tokens": 1471572, + "total_output_tokens": 11144, + "e2e_ms": { + "mean": 4993.769744873134, + "p50": 5659.099992990377, + "p90": 7970.951543792035, + "p95": 8917.362221342044, + "p99": 9676.380278440483 + }, + "ttft_ms": { + "mean": 493.3822291997785, + "p50": 310.9949789941311, + "p90": 994.0794685913728, + "p95": 1809.2214257514554, + "p99": 2638.3947925921525 + }, + "tpot_ms": { + "mean": 17.904696785791124, + "p50": 14.133043641911359, + "p90": 21.231970009860433, + "p95": 23.23206808979749, + "p99": 79.99220650661975 + }, + "itl_ms": { + "mean": 16.792353923795673, + "p50": 9.794692494324408, + "p90": 11.13799239101354, + "p95": 16.110704706807127, + "p99": 299.0010918772896 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_8_65536_512.jsonl" + }, + { + "name": "c1_i65536_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 13.631586004019482, + "request_throughput": 0.3667951769167339, + "input_token_throughput": 12750.533939979505, + "output_token_throughput": 112.31268317190393, + "total_token_throughput": 12862.846623151408, + "total_input_tokens": 173810, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 2724.9468181980774, + "p50": 1315.5071219953243, + "p90": 5638.155575603014, + "p95": 5751.589557807893, + "p99": 5842.3367435717955 + }, + "ttft_ms": { + "mean": 229.68910000054166, + "p50": 234.39669999061152, + "p90": 351.4844470017124, + "p95": 358.4967870032414, + "p99": 364.10665900446475 + }, + "tpot_ms": { + "mean": 8.071901209250624, + "p50": 8.18316470141456, + "p90": 8.256781669216025, + "p95": 8.260151384688811, + "p99": 8.262847157067041 + }, + "itl_ms": { + "mean": 8.213330314667415, + "p50": 8.222839998779818, + "p90": 8.36471018847078, + "p95": 8.409789600409567, + "p99": 8.535900008864699 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_65536_1024.jsonl" + }, + { + "name": "c8_i65536_o1024", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 1024, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 41.44024398599868, + "request_throughput": 0.9652452821830564, + "input_token_throughput": 35510.698259817116, + "output_token_throughput": 528.3752674670051, + "total_token_throughput": 36039.07352728412, + "total_input_tokens": 1471572, + "total_output_tokens": 21896, + "e2e_ms": { + "mean": 7344.833625252068, + "p50": 7517.831302000559, + "p90": 12001.890048698988, + "p95": 12591.942219049084, + "p99": 13878.417216385713 + }, + "ttft_ms": { + "mean": 576.4698123020935, + "p50": 329.346632497618, + "p90": 2113.0596766917733, + "p95": 2177.545073386862, + "p99": 2783.1520693635684 + }, + "tpot_ms": { + "mean": 13.128898573851828, + "p50": 11.72786862060573, + "p90": 16.312076118140663, + "p95": 20.41867396816347, + "p99": 32.65012742865675 + }, + "itl_ms": { + "mean": 12.65048005948215, + "p50": 9.59290299215354, + "p90": 10.794561996590346, + "p95": 11.26046699937433, + "p99": 76.53014999232255 + }, + "gpu_memory": { + "peak_used_mb": 140854.0, + "avg_used_mb": 140343.25, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_8_65536_1024.jsonl" + }, + { + "name": "c1_i131072_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 13.241434575989842, + "request_throughput": 0.37760259066387697, + "input_token_throughput": 27974.1592857064, + "output_token_throughput": 28.622276372321874, + "total_token_throughput": 28002.78156207872, + "total_input_tokens": 370418, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 2646.886209206423, + "p50": 3979.2891410179436, + "p90": 4228.74905319768, + "p95": 4297.812612593407, + "p99": 4353.063460109988 + }, + "ttft_ms": { + "mean": 2074.6922916034237, + "p50": 3200.7960340124555, + "p90": 3482.7435716055334, + "p95": 3498.4317138034385, + "p99": 3510.9822275617626 + }, + "tpot_ms": { + "mean": 7.739093047863315, + "p50": 7.695843198159633, + "p90": 8.135016023588832, + "p95": 8.184732786903622, + "p99": 8.224506197555456 + }, + "itl_ms": { + "mean": 8.220462135043283, + "p50": 8.32327950047329, + "p90": 8.480935881379992, + "p95": 8.557302453846205, + "p99": 10.57689555454996 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 140528.13888888888, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_131072_128.jsonl" + }, + { + "name": "c4_i131072_o128", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 128, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 32.8477290289884, + "request_throughput": 0.6088700982143951, + "input_token_throughput": 44885.93408387011, + "output_token_throughput": 34.6751520933098, + "total_token_throughput": 44920.60923596342, + "total_input_tokens": 1474401, + "total_output_tokens": 1139, + "e2e_ms": { + "mean": 6305.320444246172, + "p50": 6186.205157995573, + "p90": 10649.124635488264, + "p95": 12451.582126750147, + "p99": 13546.316887757273 + }, + "ttft_ms": { + "mean": 2993.023453996284, + "p50": 2445.912541996222, + "p90": 7026.627190900037, + "p95": 7688.920363315265, + "p99": 7746.948921447038 + }, + "tpot_ms": { + "mean": 55.15329067889916, + "p50": 24.824469108214664, + "p90": 150.7561264443696, + "p95": 151.39788335583992, + "p99": 157.04899968672692 + }, + "itl_ms": { + "mean": 64.00490000482382, + "p50": 8.87769999098964, + "p90": 325.44073020108044, + "p95": 378.21677869651467, + "p99": 447.43990241433494 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 140981.16935483873, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_4_131072_128.jsonl" + }, + { + "name": "c1_i131072_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 8.185897247021785, + "request_throughput": 0.6108065920103155, + "input_token_throughput": 45250.75123985541, + "output_token_throughput": 61.935788429845985, + "total_token_throughput": 45312.687028285254, + "total_input_tokens": 370418, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1636.2850127916317, + "p50": 1331.8980940093752, + "p90": 3016.347304591909, + "p95": 3468.1659967871383, + "p99": 3829.6209505433217 + }, + "ttft_ms": { + "mean": 851.0614429891575, + "p50": 396.08997298637405, + "p90": 2085.7629711856134, + "p95": 2612.0096285827453, + "p99": 3033.0069545004512 + }, + "tpot_ms": { + "mean": 7.807918549771148, + "p50": 7.733951413413233, + "p90": 8.200321834276806, + "p95": 8.22503744215863, + "p99": 8.24480992846409 + }, + "itl_ms": { + "mean": 8.21347870501333, + "p50": 8.264218995464034, + "p90": 8.509880202473141, + "p95": 8.6173327465076, + "p99": 9.081349607731688 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_131072_256.jsonl" + }, + { + "name": "c4_i131072_o256", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 256, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 25.167552392988, + "request_throughput": 0.7946740186611175, + "input_token_throughput": 58583.40838939852, + "output_token_throughput": 101.20173627649332, + "total_token_throughput": 58684.61012567501, + "total_input_tokens": 1474401, + "total_output_tokens": 2547, + "e2e_ms": { + "mean": 4833.018173197343, + "p50": 5363.060645497171, + "p90": 8616.296054696435, + "p95": 10204.22384394042, + "p99": 10875.063044800772 + }, + "ttft_ms": { + "mean": 1578.8164547033375, + "p50": 567.1622425143141, + "p90": 4755.515111584102, + "p95": 6019.33358459064, + "p99": 6092.089868128824 + }, + "tpot_ms": { + "mean": 20.617913648801018, + "p50": 11.254709681312445, + "p90": 43.49905538605527, + "p95": 43.89723899583028, + "p99": 46.902155262173146 + }, + "itl_ms": { + "mean": 27.24282930725671, + "p50": 8.897086983779445, + "p90": 12.533789791632453, + "p95": 193.9040724013352, + "p99": 383.8965240016113 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_4_131072_256.jsonl" + }, + { + "name": "c1_i131072_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 5.599419089994626, + "request_throughput": 0.892949772045871, + "input_token_throughput": 66152.9337323375, + "output_token_throughput": 90.54510688545132, + "total_token_throughput": 66243.47883922294, + "total_input_tokens": 370418, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1118.428915401455, + "p50": 1203.2813199912198, + "p90": 1598.2713803998195, + "p95": 1626.8388722033703, + "p99": 1649.6928656462112 + }, + "ttft_ms": { + "mean": 333.30124079366215, + "p50": 421.17294599302113, + "p90": 531.4979945891537, + "p95": 555.0389407901093, + "p99": 573.8716977508739 + }, + "tpot_ms": { + "mean": 7.810111934171644, + "p50": 7.718917504116539, + "p90": 8.2163644195943, + "p95": 8.244790234943565, + "p99": 8.267530887222978 + }, + "itl_ms": { + "mean": 8.195010171184853, + "p50": 8.27857299009338, + "p90": 8.465622790390626, + "p95": 8.511578515754081, + "p99": 9.422437305911433 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_131072_512.jsonl" + }, + { + "name": "c4_i131072_o512", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 512, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 19.452503250999143, + "request_throughput": 1.0281453107569964, + "input_token_throughput": 75794.92371627133, + "output_token_throughput": 302.0176850348677, + "total_token_throughput": 76096.94140130619, + "total_input_tokens": 1474401, + "total_output_tokens": 5875, + "e2e_ms": { + "mean": 3412.523278799199, + "p50": 3323.5643379885005, + "p90": 5378.397772402969, + "p95": 5788.928604766261, + "p99": 5861.600530559663 + }, + "ttft_ms": { + "mean": 489.3263924503117, + "p50": 510.96236550074536, + "p90": 651.322402607184, + "p95": 724.2809477567795, + "p99": 1360.671731956826 + }, + "tpot_ms": { + "mean": 9.942585465855233, + "p50": 9.45216913136782, + "p90": 12.93200955462183, + "p95": 13.96891684206874, + "p99": 16.164954653375492 + }, + "itl_ms": { + "mean": 10.494167114358234, + "p50": 8.834993990603834, + "p90": 9.19338600942865, + "p95": 11.618338990956545, + "p99": 66.06157450005425 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_4_131072_512.jsonl" + }, + { + "name": "c1_i262144_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 262144, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 24.683879674994387, + "request_throughput": 0.202561350396841, + "input_token_throughput": 30936.546849788258, + "output_token_throughput": 15.35415036008055, + "total_token_throughput": 30951.901000148337, + "total_input_tokens": 763634, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 4935.3012414008845, + "p50": 6083.7700930133, + "p90": 8446.296632592566, + "p95": 9036.749655794118, + "p99": 9509.11207435536 + }, + "ttft_ms": { + "mean": 4393.166679597925, + "p50": 6002.486003009835, + "p90": 7730.5542895861445, + "p95": 8221.069923788307, + "p99": 8613.482431150042 + }, + "tpot_ms": { + "mean": 6.699663761331911, + "p50": 7.274658267523988, + "p90": 7.622955134360599, + "p95": 7.641578964257113, + "p99": 7.656478028174324 + }, + "itl_ms": { + "mean": 8.339822855509388, + "p50": 8.389922004425898, + "p90": 8.624103013426065, + "p95": 8.7166765879374, + "p99": 13.3421354938764 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_262144_128.jsonl" + }, + { + "name": "c2_i262144_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 262144, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 30.757805990986526, + "request_throughput": 0.3251207190438247, + "input_token_throughput": 45318.60953959064, + "output_token_throughput": 24.57912635971315, + "total_token_throughput": 45343.18866595035, + "total_input_tokens": 1393901, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 5572.849400006817, + "p50": 6337.936259515118, + "p90": 9096.200442497502, + "p95": 9102.017221246206, + "p99": 9106.670644245169 + }, + "ttft_ms": { + "mean": 3243.136497796513, + "p50": 1354.019629987306, + "p90": 7516.959703492466, + "p95": 7994.942352740326, + "p99": 8377.328472138615 + }, + "tpot_ms": { + "mean": 25.22720349124221, + "p50": 7.827698137014959, + "p90": 67.88999795797623, + "p95": 70.27790312557251, + "p99": 72.18822725964957 + }, + "itl_ms": { + "mean": 34.92752810191563, + "p50": 8.470294997096062, + "p90": 10.573567188112062, + "p95": 352.75189329404344, + "p99": 490.42820408707513 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_2_262144_128.jsonl" + }, + { + "name": "c1_i262144_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 262144, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 7.0173407410038635, + "request_throughput": 0.712520623486886, + "input_token_throughput": 108820.99475915695, + "output_token_throughput": 72.24959122157024, + "total_token_throughput": 108893.24435037852, + "total_input_tokens": 763634, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1401.7727510014083, + "p50": 1229.8007990175392, + "p90": 2039.681368804304, + "p95": 2062.12660340243, + "p99": 2080.082791080931 + }, + "ttft_ms": { + "mean": 643.5495240089949, + "p50": 577.4397689965554, + "p90": 869.6892130130437, + "p95": 962.1196240128482, + "p99": 1036.063952812692 + }, + "tpot_ms": { + "mean": 6.921365473457675, + "p50": 7.585087851217124, + "p90": 7.831707821027708, + "p95": 7.884401405159936, + "p99": 7.926556272465718 + }, + "itl_ms": { + "mean": 8.331523793378517, + "p50": 8.391458977712318, + "p90": 8.569749590242282, + "p95": 8.623586906469427, + "p99": 12.65661973855457 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 99.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_262144_256.jsonl" + }, + { + "name": "c2_i262144_o256", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 262144, + "output_len": 256, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 20.987319235980976, + "request_throughput": 0.476478195598028, + "input_token_throughput": 66416.34333222869, + "output_token_throughput": 66.51635610548472, + "total_token_throughput": 66482.85968833417, + "total_input_tokens": 1393901, + "total_output_tokens": 1396, + "e2e_ms": { + "mean": 3491.746912599774, + "p50": 1792.6828510098858, + "p90": 7858.686492117704, + "p95": 7972.476840547461, + "p99": 8063.509119291267 + }, + "ttft_ms": { + "mean": 1808.1756318977568, + "p50": 576.1903529928531, + "p90": 6368.217996598105, + "p95": 6399.544915788283, + "p99": 6424.606451140426 + }, + "tpot_ms": { + "mean": 10.74726866873382, + "p50": 8.189858736473353, + "p90": 11.178352464814047, + "p95": 22.95827448958619, + "p99": 32.38221210940396 + }, + "itl_ms": { + "mean": 13.111567167450806, + "p50": 8.418185985647142, + "p90": 8.64076518919319, + "p95": 9.175839160161555, + "p99": 319.3491203873425 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_2_262144_256.jsonl" + }, + { + "name": "c1_i524288_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 524288, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 23.694438540987903, + "request_throughput": 0.21101998223552473, + "input_token_throughput": 43291.93106751842, + "output_token_throughput": 15.995314653452775, + "total_token_throughput": 43307.92638217187, + "total_input_tokens": 1025778, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 4736.943290999625, + "p50": 1072.3386270110495, + "p90": 12170.458413806047, + "p95": 15565.541827410922, + "p99": 18281.60855829483 + }, + "ttft_ms": { + "mean": 4207.112867000978, + "p50": 589.2991840082686, + "p90": 11375.42073140503, + "p95": 14806.511789211068, + "p99": 17551.384635455906 + }, + "tpot_ms": { + "mean": 6.62686549688025, + "p50": 7.088454843124412, + "p90": 7.382344723550501, + "p95": 7.422827795678168, + "p99": 7.455214253380301 + }, + "itl_ms": { + "mean": 8.436058923582825, + "p50": 8.478927513351664, + "p90": 8.69316780299414, + "p95": 8.776555457734501, + "p99": 15.353498535696419 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_524288_128.jsonl" + }, + { + "name": "c2_i524288_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 524288, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 15.610297531005926, + "request_throughput": 0.640602780320972, + "input_token_throughput": 106086.7031336644, + "output_token_throughput": 48.42957019226548, + "total_token_throughput": 106135.13270385667, + "total_input_tokens": 1656045, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 3078.7888674007263, + "p50": 1312.8249200090067, + "p90": 9615.761693101376, + "p95": 10277.547583042176, + "p99": 10806.97629499482 + }, + "ttft_ms": { + "mean": 1630.8294385031331, + "p50": 558.4827779966872, + "p90": 2401.2759010103737, + "p95": 6241.666616495049, + "p99": 9313.979188882804 + }, + "tpot_ms": { + "mean": 44.5421275913291, + "p50": 7.944679463915087, + "p90": 45.886444982105864, + "p95": 213.85856155622668, + "p99": 348.236254815524 + }, + "itl_ms": { + "mean": 22.76590438676799, + "p50": 8.449637491139583, + "p90": 10.348231488023885, + "p95": 26.07415175589267, + "p99": 423.9938117956624 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_2_524288_128.jsonl" + }, + { + "name": "c1_i1048576_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1048576, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 77.70366387499962, + "request_throughput": 0.06434703012258731, + "input_token_throughput": 19948.428718799685, + "output_token_throughput": 4.877504883292118, + "total_token_throughput": 19953.306223682976, + "total_input_tokens": 1550066, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 15539.210548391566, + "p50": 5986.594451009296, + "p90": 37508.767122181605, + "p95": 43599.43183357827, + "p99": 48471.96360269561 + }, + "ttft_ms": { + "mean": 15035.420496592997, + "p50": 5905.091491993517, + "p90": 37049.968937598176, + "p95": 43228.075727797106, + "p99": 48170.56115995626 + }, + "tpot_ms": { + "mean": 6.144359419189403, + "p50": 7.069847264610158, + "p90": 7.45164397401612, + "p95": 7.510030491148652, + "p99": 7.556739704854678 + }, + "itl_ms": { + "mean": 8.596305214818218, + "p50": 8.52145001408644, + "p90": 8.81586839677766, + "p95": 8.945846802089362, + "p99": 16.056178179569308 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_1_1048576_128.jsonl" + }, + { + "name": "c2_i1048576_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 1048576, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 165.96181306999642, + "request_throughput": 0.06025482498062598, + "input_token_throughput": 19455.734667336805, + "output_token_throughput": 4.5552647685353245, + "total_token_throughput": 19460.28993210534, + "total_input_tokens": 3228909, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 31427.722522203112, + "p50": 33637.77801199467, + "p90": 54266.53705881035, + "p95": 55532.931616414855, + "p99": 56546.04726249847 + }, + "ttft_ms": { + "mean": 19476.10798960377, + "p50": 9854.220522014657, + "p90": 49815.4517834133, + "p95": 51577.88556921587, + "p99": 52987.83259785792 + }, + "tpot_ms": { + "mean": 277.944045389714, + "p50": 72.84710567608471, + "p90": 651.8447391012355, + "p95": 766.4053257987784, + "p99": 858.0537951568133 + }, + "itl_ms": { + "mean": 212.66139607297154, + "p50": 8.927634509745985, + "p90": 760.9854289854413, + "p95": 891.9243723576071, + "p99": 1024.846997949644 + }, + "gpu_memory": { + "peak_used_mb": 141374.0, + "avg_used_mb": 141124.75, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/raw_outputs/vllm_main_2_1048576_128.jsonl" + } + ] +} \ No newline at end of file diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/scenarios.tsv b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/scenarios.tsv new file mode 100644 index 0000000..3717ac1 --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp4_dp2/scenarios.tsv @@ -0,0 +1,57 @@ +mark input_len output_len concurrency num_prompts +Y 1024 128 1 5 +Y 1024 128 128 640 +Y 1024 256 1 5 +Y 1024 256 128 640 +Y 1024 512 1 5 +Y 1024 512 128 640 +Y 1024 1024 1 5 +Y 1024 1024 128 640 +Y 1024 2048 1 5 +Y 1024 2048 128 640 +Y 1024 4096 1 5 +Y 1024 4096 128 640 +Y 4096 128 1 5 +Y 4096 128 64 320 +Y 4096 256 1 5 +Y 4096 256 64 320 +Y 4096 512 1 5 +Y 4096 512 64 320 +Y 4096 1024 1 5 +Y 4096 1024 64 320 +Y 4096 2048 1 5 +Y 4096 2048 64 320 +Y 4096 4096 1 5 +Y 4096 4096 64 320 +Y 16384 128 1 5 +Y 16384 128 32 160 +Y 16384 256 1 5 +Y 16384 256 32 160 +Y 16384 512 1 5 +Y 16384 512 32 160 +Y 16384 1024 1 5 +Y 16384 1024 32 160 +Y 16384 2048 1 5 +Y 16384 2048 32 160 +Y 65536 128 1 5 +Y 65536 128 8 40 +Y 65536 256 1 5 +Y 65536 256 8 40 +Y 65536 512 1 5 +Y 65536 512 8 40 +Y 65536 1024 1 5 +Y 65536 1024 8 40 +Y 131072 128 1 5 +Y 131072 128 4 20 +Y 131072 256 1 5 +Y 131072 256 4 20 +Y 131072 512 1 5 +Y 131072 512 4 20 +Y 262144 128 1 5 +Y 262144 128 2 10 +Y 262144 256 1 5 +Y 262144 256 2 10 +Y 524288 128 1 5 +Y 524288 128 2 10 +Y 1048576 128 1 5 +Y 1048576 128 2 10 diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/report.md b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/report.md new file mode 100644 index 0000000..36bdfcf --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/report.md @@ -0,0 +1,70 @@ +# 8x NVIDIA H200 143GB VLLM Benchmark Report + +- Result root: `/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1` +- Model: `/data/models/DeepSeek-V4-Flash` +- Backend: VLLM +- Benchmark client: `sglang.bench_serving --backend vllm` + +## Results + +| Scenario | Phase | Concurrency | Input | Output | Duration(s) | Success | Req/s | In tok/s | Out tok/s | Total tok/s | Mean TTFT(ms) | P95 TTFT(ms) | P99 TTFT(ms) | Mean TPOT(ms) | P95 TPOT(ms) | P99 TPOT(ms) | Mean E2E(ms) | P95 E2E(ms) | P99 E2E(ms) | Peak GPU mem | SLO | +|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| +| c1_i1024_o128 | main | 1 | 1024 | 128 | 3.11 | 5 | 1.61 | 571.42 | 121.80 | 693.22 | 117.30 | 274.43 | 314.97 | 6.74 | 6.78 | 6.79 | 620.97 | 851.31 | 871.45 | 131900/143771 MiB (91.7%) | ✅ | +| c128_i1024_o128 | main | 128 | 1024 | 128 | 25.39 | 640 | 25.21 | 13188.24 | 1644.87 | 14833.11 | 486.29 | 1647.93 | 2127.36 | 71.51 | 108.98 | 146.42 | 4876.35 | 10467.31 | 11987.25 | 132930/143771 MiB (92.5%) | ⚠️ | +| c1_i1024_o256 | main | 1 | 1024 | 256 | 3.58 | 5 | 1.40 | 497.17 | 141.77 | 638.94 | 40.11 | 44.63 | 45.58 | 6.71 | 6.72 | 6.72 | 713.89 | 1209.48 | 1281.54 | 132930/143771 MiB (92.5%) | ✅ | +| c128_i1024_o256 | main | 128 | 1024 | 256 | 27.46 | 640 | 23.31 | 12194.74 | 3082.56 | 15277.30 | 258.20 | 725.46 | 741.75 | 37.61 | 47.17 | 56.15 | 5081.28 | 9930.41 | 10662.58 | 132930/143771 MiB (92.5%) | ✅ | +| c1_i1024_o512 | main | 1 | 1024 | 512 | 3.69 | 5 | 1.36 | 482.38 | 137.55 | 619.93 | 60.69 | 65.04 | 65.69 | 6.74 | 6.78 | 6.79 | 735.69 | 1233.35 | 1305.74 | 132930/143771 MiB (92.5%) | ✅ | +| c128_i1024_o512 | main | 128 | 1024 | 512 | 37.45 | 640 | 17.09 | 8940.37 | 4330.93 | 13271.30 | 211.37 | 760.28 | 777.02 | 26.29 | 29.37 | 34.23 | 6728.56 | 13132.89 | 14073.81 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i1024_o1024 | main | 1 | 1024 | 1024 | 10.48 | 5 | 0.48 | 169.65 | 146.08 | 315.74 | 48.51 | 60.67 | 60.68 | 6.71 | 6.73 | 6.73 | 2094.65 | 4631.94 | 4727.62 | 132932/143771 MiB (92.5%) | ✅ | +| c128_i1024_o1024 | main | 128 | 1024 | 1024 | 68.42 | 640 | 9.35 | 4893.76 | 4727.69 | 9621.45 | 198.71 | 724.06 | 738.02 | 24.27 | 25.99 | 28.67 | 12260.92 | 23755.36 | 25355.91 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i1024_o2048 | main | 1 | 1024 | 2048 | 37.94 | 5 | 0.13 | 46.87 | 148.32 | 195.19 | 46.74 | 60.19 | 62.81 | 6.71 | 6.72 | 6.72 | 7585.93 | 11492.67 | 11586.89 | 132932/143771 MiB (92.5%) | ✅ | +| c128_i1024_o2048 | main | 128 | 1024 | 2048 | 133.47 | 640 | 4.80 | 2508.84 | 4871.12 | 7379.96 | 198.26 | 746.05 | 761.60 | 23.37 | 24.26 | 24.89 | 23639.36 | 44752.06 | 48201.59 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i1024_o4096 | main | 1 | 1024 | 4096 | 79.46 | 5 | 0.06 | 22.38 | 148.14 | 170.51 | 42.13 | 46.60 | 47.48 | 6.73 | 6.76 | 6.76 | 15890.77 | 24601.03 | 25332.98 | 132932/143771 MiB (92.5%) | ✅ | +| c128_i1024_o4096 | main | 128 | 1024 | 4096 | 275.08 | 640 | 2.33 | 1217.30 | 4775.68 | 5992.98 | 218.44 | 736.09 | 756.63 | 23.99 | 25.92 | 26.62 | 48923.09 | 92762.87 | 97316.79 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i4096_o128 | main | 1 | 4096 | 128 | 3.09 | 5 | 1.62 | 3231.34 | 122.84 | 3354.18 | 113.28 | 148.51 | 155.20 | 6.72 | 6.74 | 6.74 | 615.65 | 898.15 | 918.13 | 132932/143771 MiB (92.5%) | ✅ | +| c64_i4096_o128 | main | 64 | 4096 | 128 | 27.10 | 320 | 11.81 | 24931.54 | 772.92 | 25704.46 | 705.87 | 2978.27 | 3725.28 | 76.32 | 108.07 | 233.29 | 5252.69 | 10435.23 | 11989.51 | 132932/143771 MiB (92.5%) | ⚠️ | +| c1_i4096_o256 | main | 1 | 4096 | 256 | 3.66 | 5 | 1.37 | 2724.98 | 138.57 | 2863.55 | 54.71 | 67.18 | 67.54 | 6.73 | 6.77 | 6.78 | 731.14 | 1243.27 | 1320.30 | 132932/143771 MiB (92.5%) | ✅ | +| c64_i4096_o256 | main | 64 | 4096 | 256 | 16.45 | 320 | 19.45 | 41074.35 | 2518.43 | 43592.78 | 216.47 | 804.28 | 815.33 | 22.25 | 25.88 | 28.53 | 2990.66 | 5802.25 | 6644.63 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i4096_o512 | main | 1 | 4096 | 512 | 3.66 | 5 | 1.37 | 2724.45 | 138.55 | 2863.00 | 53.85 | 64.63 | 65.10 | 6.73 | 6.78 | 6.78 | 730.54 | 1243.77 | 1320.67 | 132932/143771 MiB (92.5%) | ✅ | +| c64_i4096_o512 | main | 64 | 4096 | 512 | 27.32 | 320 | 11.71 | 24731.28 | 3100.03 | 27831.30 | 174.83 | 584.91 | 601.95 | 17.83 | 18.78 | 19.95 | 4860.53 | 9051.41 | 9668.74 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i4096_o1024 | main | 1 | 4096 | 1024 | 10.58 | 5 | 0.47 | 942.72 | 144.76 | 1087.48 | 54.50 | 66.58 | 66.81 | 6.73 | 6.78 | 6.79 | 2113.75 | 4687.47 | 4791.74 | 132932/143771 MiB (92.5%) | ✅ | +| c64_i4096_o1024 | main | 64 | 4096 | 1024 | 52.14 | 320 | 6.14 | 12958.58 | 3283.93 | 16242.51 | 197.14 | 789.79 | 800.08 | 17.06 | 17.95 | 19.33 | 9239.51 | 17164.77 | 17906.82 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i4096_o2048 | main | 1 | 4096 | 2048 | 38.30 | 5 | 0.13 | 260.29 | 146.91 | 407.20 | 55.00 | 67.22 | 67.42 | 6.75 | 6.79 | 6.80 | 7659.17 | 11647.12 | 11755.04 | 132932/143771 MiB (92.5%) | ✅ | +| c64_i4096_o2048 | main | 64 | 4096 | 2048 | 97.69 | 320 | 3.28 | 6916.20 | 3408.88 | 10325.08 | 162.14 | 570.75 | 582.03 | 16.56 | 17.06 | 18.07 | 17265.87 | 32918.48 | 34336.54 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i4096_o4096 | main | 1 | 4096 | 4096 | 79.98 | 5 | 0.06 | 124.66 | 147.18 | 271.85 | 55.41 | 66.70 | 66.85 | 6.77 | 6.80 | 6.80 | 15993.58 | 24761.64 | 25525.53 | 132932/143771 MiB (92.5%) | ✅ | +| c64_i4096_o4096 | main | 64 | 4096 | 4096 | 192.01 | 320 | 1.67 | 3518.79 | 3408.94 | 6927.73 | 163.81 | 576.41 | 599.00 | 16.44 | 16.79 | 16.98 | 33560.76 | 65515.45 | 68183.67 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i16384_o128 | main | 1 | 16384 | 128 | 3.74 | 5 | 1.34 | 11422.24 | 101.29 | 11523.54 | 244.24 | 433.34 | 440.01 | 6.72 | 6.80 | 6.80 | 746.96 | 1184.46 | 1242.36 | 132932/143771 MiB (92.5%) | ✅ | +| c32_i16384_o128 | main | 32 | 16384 | 128 | 29.67 | 160 | 5.39 | 43522.36 | 356.17 | 43878.53 | 996.18 | 3789.36 | 4532.55 | 78.86 | 150.73 | 226.61 | 5789.68 | 10661.97 | 11830.35 | 132932/143771 MiB (92.5%) | ❌ | +| c1_i16384_o256 | main | 1 | 16384 | 256 | 3.82 | 5 | 1.31 | 11173.76 | 132.55 | 11306.32 | 87.44 | 122.35 | 122.83 | 6.73 | 6.76 | 6.76 | 763.51 | 1299.07 | 1372.37 | 132932/143771 MiB (92.5%) | ✅ | +| c32_i16384_o256 | main | 32 | 16384 | 256 | 12.46 | 160 | 12.84 | 103604.79 | 1782.54 | 105387.34 | 200.10 | 636.48 | 644.96 | 14.84 | 16.94 | 20.78 | 2229.45 | 3832.96 | 4262.99 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i16384_o512 | main | 1 | 16384 | 512 | 3.81 | 5 | 1.31 | 11209.67 | 132.98 | 11342.65 | 85.20 | 118.65 | 119.23 | 6.73 | 6.76 | 6.76 | 761.16 | 1293.05 | 1365.21 | 132932/143771 MiB (92.5%) | ✅ | +| c32_i16384_o512 | main | 32 | 16384 | 512 | 20.43 | 160 | 7.83 | 63203.51 | 1977.19 | 65180.70 | 190.69 | 640.86 | 739.06 | 14.04 | 15.70 | 18.53 | 3673.45 | 7038.21 | 7504.82 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i16384_o1024 | main | 1 | 16384 | 1024 | 10.85 | 5 | 0.46 | 3939.68 | 141.13 | 4080.81 | 96.12 | 132.08 | 134.06 | 6.75 | 6.80 | 6.81 | 2168.26 | 4767.81 | 4873.19 | 132932/143771 MiB (92.5%) | ✅ | +| c32_i16384_o1024 | main | 32 | 16384 | 1024 | 40.02 | 160 | 4.00 | 32262.84 | 2122.35 | 34385.19 | 226.08 | 789.94 | 950.40 | 13.38 | 14.23 | 22.02 | 7223.57 | 13034.14 | 13797.93 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i16384_o2048 | main | 1 | 16384 | 2048 | 38.62 | 5 | 0.13 | 1106.58 | 145.70 | 1252.28 | 92.60 | 132.65 | 135.00 | 6.77 | 6.82 | 6.82 | 7722.67 | 11757.03 | 11867.20 | 132932/143771 MiB (92.5%) | ✅ | +| c32_i16384_o2048 | main | 32 | 16384 | 2048 | 82.31 | 160 | 1.94 | 15686.47 | 2226.25 | 17912.73 | 187.67 | 628.02 | 806.24 | 12.88 | 13.39 | 14.85 | 14894.46 | 25291.54 | 26578.49 | 132932/143771 MiB (92.5%) | ✅ | +| c1_i65536_o128 | main | 1 | 65536 | 128 | 5.98 | 5 | 0.84 | 29066.05 | 63.38 | 29129.43 | 697.62 | 1783.81 | 1903.90 | 6.67 | 6.75 | 6.75 | 1194.51 | 2550.76 | 2686.50 | 133260/143771 MiB (92.7%) | ✅ | +| c8_i65536_o128 | main | 8 | 65536 | 128 | 39.65 | 40 | 1.01 | 37118.27 | 64.77 | 37183.05 | 3209.81 | 7445.34 | 8645.53 | 88.42 | 248.75 | 263.80 | 7821.82 | 14289.92 | 16484.17 | 133780/143771 MiB (93.1%) | ❌ | +| c1_i65536_o256 | main | 1 | 65536 | 256 | 4.21 | 5 | 1.19 | 41330.67 | 120.56 | 41451.23 | 161.62 | 254.47 | 256.20 | 6.74 | 6.79 | 6.80 | 839.71 | 1306.35 | 1352.80 | 133780/143771 MiB (93.1%) | ✅ | +| c8_i65536_o256 | main | 8 | 65536 | 256 | 8.64 | 40 | 4.63 | 170252.44 | 608.09 | 170860.53 | 356.04 | 749.11 | 864.77 | 9.14 | 10.21 | 10.30 | 1581.50 | 2865.09 | 2998.37 | 133780/143771 MiB (93.1%) | ✅ | +| c1_i65536_o512 | main | 1 | 65536 | 512 | 4.23 | 5 | 1.18 | 41120.06 | 119.95 | 41240.01 | 184.79 | 288.97 | 290.20 | 6.54 | 6.74 | 6.75 | 843.98 | 1310.36 | 1356.99 | 133780/143771 MiB (93.1%) | ✅ | +| c8_i65536_o512 | main | 8 | 65536 | 512 | 15.79 | 40 | 2.53 | 93186.96 | 705.69 | 93892.65 | 274.50 | 661.39 | 679.12 | 9.10 | 9.63 | 10.39 | 2813.45 | 5054.25 | 5200.71 | 133780/143771 MiB (93.1%) | ✅ | +| c1_i65536_o1024 | main | 1 | 65536 | 1024 | 11.22 | 5 | 0.45 | 15489.07 | 136.44 | 15625.51 | 161.17 | 254.42 | 254.84 | 6.76 | 6.85 | 6.86 | 2242.90 | 4765.81 | 4841.93 | 133780/143771 MiB (93.1%) | ✅ | +| c8_i65536_o1024 | main | 8 | 65536 | 1024 | 29.80 | 40 | 1.34 | 49382.35 | 734.78 | 50117.12 | 281.66 | 671.08 | 707.77 | 8.91 | 9.20 | 10.49 | 5146.09 | 8994.81 | 9476.99 | 133780/143771 MiB (93.1%) | ✅ | +| c1_i131072_o128 | main | 1 | 131072 | 128 | 9.02 | 5 | 0.55 | 41083.10 | 42.03 | 41125.13 | 1332.75 | 3042.40 | 3072.01 | 6.34 | 6.70 | 6.72 | 1801.84 | 3782.08 | 3832.09 | 133780/143771 MiB (93.1%) | ⚠️ | +| c4_i131072_o128 | main | 4 | 131072 | 128 | 24.36 | 20 | 0.82 | 60525.08 | 46.76 | 60571.83 | 2268.91 | 5665.45 | 7563.45 | 46.92 | 130.55 | 135.39 | 4786.17 | 9054.74 | 9263.16 | 134302/143771 MiB (93.4%) | ⚠️ | +| c1_i131072_o256 | main | 1 | 131072 | 256 | 4.85 | 5 | 1.03 | 76336.33 | 104.48 | 76440.81 | 324.28 | 526.13 | 531.79 | 6.38 | 6.74 | 6.75 | 969.07 | 1348.49 | 1365.14 | 134302/143771 MiB (93.4%) | ✅ | +| c4_i131072_o256 | main | 4 | 131072 | 256 | 8.32 | 20 | 2.40 | 177141.68 | 306.01 | 177447.69 | 542.06 | 826.11 | 873.84 | 7.11 | 8.42 | 8.69 | 1532.39 | 2573.00 | 2602.99 | 134302/143771 MiB (93.4%) | ✅ | +| c1_i131072_o512 | main | 1 | 131072 | 512 | 4.87 | 5 | 1.03 | 76048.83 | 104.09 | 76152.92 | 327.91 | 528.58 | 529.52 | 6.38 | 6.74 | 6.75 | 972.74 | 1353.22 | 1365.66 | 134302/143771 MiB (93.4%) | ✅ | +| c4_i131072_o512 | main | 4 | 131072 | 512 | 15.36 | 20 | 1.30 | 95969.05 | 382.40 | 96351.45 | 384.13 | 581.21 | 686.73 | 7.67 | 8.27 | 8.30 | 2674.27 | 3889.94 | 4365.16 | 134302/143771 MiB (93.4%) | ✅ | +| c1_i262144_o128 | main | 1 | 262144 | 128 | 21.96 | 5 | 0.23 | 34775.53 | 17.26 | 34792.78 | 3949.96 | 7547.16 | 7933.13 | 5.31 | 6.25 | 6.26 | 4389.70 | 8216.37 | 8667.71 | 134304/143771 MiB (93.4%) | ⚠️ | +| c2_i262144_o128 | main | 2 | 262144 | 128 | 17.30 | 10 | 0.58 | 80576.29 | 43.70 | 80619.99 | 1811.47 | 6405.29 | 6864.92 | 12.04 | 40.84 | 63.02 | 2911.30 | 7493.52 | 7624.83 | 134304/143771 MiB (93.4%) | ⚠️ | +| c1_i262144_o256 | main | 1 | 262144 | 256 | 5.49 | 5 | 0.91 | 139043.08 | 92.31 | 139135.39 | 483.52 | 741.06 | 802.19 | 5.45 | 6.50 | 6.55 | 1096.55 | 1644.68 | 1664.47 | 134304/143771 MiB (93.4%) | ✅ | +| c2_i262144_o256 | main | 2 | 262144 | 256 | 8.16 | 10 | 1.23 | 170921.30 | 171.18 | 171092.48 | 588.20 | 872.87 | 960.16 | 6.69 | 7.16 | 7.25 | 1528.35 | 2101.10 | 2191.39 | 134304/143771 MiB (93.4%) | ✅ | +| c1_i524288_o128 | main | 1 | 524288 | 128 | 21.47 | 5 | 0.23 | 47769.55 | 17.65 | 47787.20 | 3868.11 | 13982.40 | 16622.77 | 5.18 | 6.10 | 6.17 | 4292.93 | 14596.89 | 17210.26 | 134304/143771 MiB (93.4%) | ⚠️ | +| c2_i524288_o128 | main | 2 | 524288 | 128 | 5.67 | 10 | 1.76 | 292108.80 | 133.35 | 292242.15 | 645.47 | 1167.12 | 1232.75 | 5.64 | 6.90 | 6.94 | 1126.39 | 1682.93 | 1708.86 | 134306/143771 MiB (93.4%) | ✅ | +| c1_i1048576_o128 | main | 1 | 1048576 | 128 | 52.22 | 5 | 0.10 | 29684.37 | 7.26 | 29691.63 | 10048.05 | 38265.96 | 45702.81 | 4.67 | 6.04 | 6.08 | 10442.12 | 38536.13 | 45912.47 | 134310/143771 MiB (93.4%) | ⚠️ | +| c2_i1048576_o128 | main | 2 | 1048576 | 128 | 122.76 | 10 | 0.08 | 26303.08 | 6.16 | 26309.24 | 23067.17 | 59936.57 | 60383.98 | 15.73 | 56.69 | 68.50 | 24549.49 | 63918.14 | 66073.78 | 134312/143771 MiB (93.4%) | ⚠️ | + +SLO: S2 tier — TTFT P95 < 3000ms, TPOT mean < 50ms. ✅ pass, ⚠️ partial, ❌ fail. + diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/results.json b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/results.json new file mode 100644 index 0000000..12fb5cb --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/results.json @@ -0,0 +1,3500 @@ +{ + "metadata": { + "experiment": "dsv4_h200_vllm_tp_dp_matrix_tp8_dp1", + "run_id": "20260709-152419_matrix", + "timestamp": "2026-07-09T17:51:10+00:00", + "model": "/data/models/DeepSeek-V4-Flash", + "backend": "vllm", + "engine": "vllm", + "hardware": "8x NVIDIA H200 143GB", + "accelerator": "NVIDIA H200", + "chip": "nvidia_h200", + "script": "experiments/dsv4_h200_vllm_tp_dp_matrix/run_bench.sh", + "env": "/data/user1/yy/envs/vllm", + "git_commit": "6fce89c", + "git_dirty": "dirty", + "description": "H200 vLLM TP×DP matrix for DeepSeek-V4-Flash" + }, + "config": { + "tp": 8, + "dp": 1, + "cuda_visible_devices": "0,1,2,3,4,5,6,7", + "backend": "vllm", + "server_start_script": "experiments/dsv4_h200_vllm_tp_dp_matrix/start_vllm_dp.sh", + "server_args": "vllm serve /data/models/DeepSeek-V4-Flash --trust-remote-code --kv-cache-dtype fp8 --block-size 256 --tensor-parallel-size 8 --no-enable-flashinfer-autotune --port 30030 " + }, + "scenarios": [ + { + "name": "c1_i1024_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.1115733530023135, + "request_throughput": 1.6069041069449865, + "input_token_throughput": 571.4151004296372, + "output_token_throughput": 121.80333130642998, + "total_token_throughput": 693.2184317360671, + "total_input_tokens": 1778, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 620.9731928014662, + "p50": 539.9669890175574, + "p90": 826.1470417899545, + "p95": 851.3148173864465, + "p99": 871.4490378636401 + }, + "ttft_ms": { + "mean": 117.30040179681964, + "p50": 64.00562298949808, + "p90": 223.75530900317247, + "p95": 274.43198401015246, + "p99": 314.9733240157366 + }, + "tpot_ms": { + "mean": 6.744468233886082, + "p50": 6.731746000107652, + "p90": 6.775324689903452, + "p95": 6.78309076979834, + "p99": 6.78930363371425 + }, + "itl_ms": { + "mean": 6.732948214054745, + "p50": 6.699120509438217, + "p90": 6.850680703064427, + "p95": 6.90187855361728, + "p99": 8.64518792688613 + }, + "gpu_memory": { + "peak_used_mb": 131900.0, + "avg_used_mb": 131900.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_1024_128.jsonl" + }, + { + "name": "c128_i1024_o128", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 128, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 25.39041935800924, + "request_throughput": 25.206357995742053, + "input_token_throughput": 13188.242197912821, + "output_token_throughput": 1644.8723989596424, + "total_token_throughput": 14833.114596872463, + "total_input_tokens": 334855, + "total_output_tokens": 41764, + "e2e_ms": { + "mean": 4876.350990326864, + "p50": 4396.088168999995, + "p90": 8972.985691693613, + "p95": 10467.312990417122, + "p99": 11987.250543742266 + }, + "ttft_ms": { + "mean": 486.2943946186988, + "p50": 297.0849985140376, + "p90": 1172.9323532112176, + "p95": 1647.9308876645518, + "p99": 2127.3599312192528 + }, + "tpot_ms": { + "mean": 71.50531383675863, + "p50": 68.03394203979266, + "p90": 100.23968791809875, + "p95": 108.98483476371113, + "p99": 146.42384668454534 + }, + "itl_ms": { + "mean": 68.34565651707587, + "p50": 23.442019009962678, + "p90": 165.77782639069483, + "p95": 176.94342100294307, + "p99": 287.3323047114536 + }, + "gpu_memory": { + "peak_used_mb": 132930.0, + "avg_used_mb": 132425.22448979592, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_128_1024_128.jsonl" + }, + { + "name": "c1_i1024_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.576241757022217, + "request_throughput": 1.3981157706081049, + "input_token_throughput": 497.1699680282421, + "output_token_throughput": 141.76893913966185, + "total_token_throughput": 638.938907167904, + "total_input_tokens": 1778, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 713.893802597886, + "p50": 723.9885129965842, + "p90": 1119.4012374093293, + "p95": 1209.478307212703, + "p99": 1281.539963055402 + }, + "ttft_ms": { + "mean": 40.11499620391987, + "p50": 39.00022400193848, + "p90": 43.437266402179375, + "p95": 44.628948206081986, + "p99": 45.582293649204075 + }, + "tpot_ms": { + "mean": 6.712814833205494, + "p50": 6.714892661785969, + "p90": 6.715674534001772, + "p95": 6.715708891758421, + "p99": 6.715736377963742 + }, + "itl_ms": { + "mean": 6.710483619478992, + "p50": 6.695525997201912, + "p90": 6.968245579628274, + "p95": 7.05675591743784, + "p99": 7.320103088568431 + }, + "gpu_memory": { + "peak_used_mb": 132930.0, + "avg_used_mb": 132930.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_1024_256.jsonl" + }, + { + "name": "c128_i1024_o256", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 256, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 27.458979611023096, + "request_throughput": 23.30749390786099, + "input_token_throughput": 12194.735738307489, + "output_token_throughput": 3082.5617411515404, + "total_token_throughput": 15277.297479459028, + "total_input_tokens": 334855, + "total_output_tokens": 84644, + "e2e_ms": { + "mean": 5081.282830074133, + "p50": 4903.469455995946, + "p90": 9170.879973901903, + "p95": 9930.409122745914, + "p99": 10662.57701508439 + }, + "ttft_ms": { + "mean": 258.1973640362321, + "p50": 173.7810085178353, + "p90": 552.6221598003758, + "p95": 725.4641677965992, + "p99": 741.747970864817 + }, + "tpot_ms": { + "mean": 37.60625974624434, + "p50": 38.062800910555985, + "p90": 44.329389671741716, + "p95": 47.17057905603296, + "p99": 56.149049528066804 + }, + "itl_ms": { + "mean": 36.76333383779741, + "p50": 23.366706998785958, + "p90": 60.13022359111347, + "p95": 96.74666440114366, + "p99": 175.20204528060276 + }, + "gpu_memory": { + "peak_used_mb": 132930.0, + "avg_used_mb": 132930.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_128_1024_256.jsonl" + }, + { + "name": "c1_i1024_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.68587921600556, + "request_throughput": 1.3565284446348655, + "input_token_throughput": 482.3815149121582, + "output_token_throughput": 137.55198428597538, + "total_token_throughput": 619.9334991981335, + "total_input_tokens": 1778, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 735.6866433983669, + "p50": 742.1285230084322, + "p90": 1142.8636193915736, + "p95": 1233.3502841880543, + "p99": 1305.7396160252392 + }, + "ttft_ms": { + "mean": 60.687745799077675, + "p50": 61.6830279759597, + "p90": 64.22489199903794, + "p95": 65.0386460009031, + "p99": 65.68964920239523 + }, + "tpot_ms": { + "mean": 6.735674190831488, + "p50": 6.728461088142449, + "p90": 6.764326388062254, + "p95": 6.7760316441065145, + "p99": 6.785395848941923 + }, + "itl_ms": { + "mean": 6.722634358540738, + "p50": 6.6887545108329505, + "p90": 6.855826204991899, + "p95": 6.903062094352208, + "p99": 7.3225617126445295 + }, + "gpu_memory": { + "peak_used_mb": 132930.0, + "avg_used_mb": 132930.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_1024_512.jsonl" + }, + { + "name": "c128_i1024_o512", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 512, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 37.454274895979324, + "request_throughput": 17.08750207492879, + "input_token_throughput": 8940.367980156687, + "output_token_throughput": 4330.93419777867, + "total_token_throughput": 13271.302177935358, + "total_input_tokens": 334855, + "total_output_tokens": 162212, + "e2e_ms": { + "mean": 6728.558528907206, + "p50": 6503.705489492859, + "p90": 12159.59878990543, + "p95": 13132.893477000467, + "p99": 14073.808510748788 + }, + "ttft_ms": { + "mean": 211.3740406251054, + "p50": 116.70142400544137, + "p90": 558.8830624881666, + "p95": 760.2822678250959, + "p99": 777.0182164228754 + }, + "tpot_ms": { + "mean": 26.292669162728608, + "p50": 26.72706325471736, + "p90": 28.302211153833543, + "p95": 29.36632828523293, + "p99": 34.23378473595377 + }, + "itl_ms": { + "mean": 25.846200514553402, + "p50": 22.78870699228719, + "p90": 34.93604898103513, + "p95": 37.07805039011873, + "p99": 89.45705803576855 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132931.16417910447, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_128_1024_512.jsonl" + }, + { + "name": "c1_i1024_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 10.480287076003151, + "request_throughput": 0.4770861679398616, + "input_token_throughput": 169.65184131941479, + "output_token_throughput": 146.0837846231856, + "total_token_throughput": 315.7356259426004, + "total_input_tokens": 1778, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 2094.6468008100055, + "p50": 850.2973650174681, + "p90": 4512.331283814274, + "p95": 4631.936234416207, + "p99": 4727.620194897754 + }, + "ttft_ms": { + "mean": 48.51190840709023, + "p50": 44.887225987622514, + "p90": 60.66339420503937, + "p95": 60.67136460333131, + "p99": 60.67774092196487 + }, + "tpot_ms": { + "mean": 6.711405225664204, + "p50": 6.707264200667851, + "p90": 6.725284867411174, + "p95": 6.73001691964462, + "p99": 6.733802561431377 + }, + "itl_ms": { + "mean": 6.704089605504419, + "p50": 6.692452501738444, + "p90": 6.84615749923978, + "p95": 6.903180488734506, + "p99": 7.070738494803663 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_1024_1024.jsonl" + }, + { + "name": "c128_i1024_o1024", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 1024, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 68.42493821599055, + "request_throughput": 9.35331498553601, + "input_token_throughput": 4893.756702315094, + "output_token_throughput": 4727.691517657836, + "total_token_throughput": 9621.44821997293, + "total_input_tokens": 334855, + "total_output_tokens": 323492, + "e2e_ms": { + "mean": 12260.91877303138, + "p50": 12370.803522499045, + "p90": 22112.71922251035, + "p95": 23755.357677354186, + "p99": 25355.91061090352 + }, + "ttft_ms": { + "mean": 198.70940640835215, + "p50": 110.31356250168756, + "p90": 590.7794083002955, + "p95": 724.0565157524542, + "p99": 738.0223441249109 + }, + "tpot_ms": { + "mean": 24.27136748121635, + "p50": 24.670942883774895, + "p90": 25.631626756557917, + "p95": 25.98724100797857, + "p99": 28.667557228618534 + }, + "itl_ms": { + "mean": 23.925414834838133, + "p50": 22.627816011663526, + "p90": 31.98559701559134, + "p95": 34.510503988713026, + "p99": 38.06540880468675 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_128_1024_1024.jsonl" + }, + { + "name": "c1_i1024_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 37.93773976698867, + "request_throughput": 0.13179488368863568, + "input_token_throughput": 46.86626063967884, + "output_token_throughput": 148.32196210319057, + "total_token_throughput": 195.18822274286944, + "total_input_tokens": 1778, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 7585.934515192639, + "p50": 7374.917035980616, + "p90": 11374.88244700362, + "p95": 11492.666910006665, + "p99": 11586.8944804091 + }, + "ttft_ms": { + "mean": 46.74239640007727, + "p50": 42.968800000380725, + "p90": 56.913516198983416, + "p95": 60.18717059050687, + "p99": 62.806094103725634 + }, + "tpot_ms": { + "mean": 6.707419037359887, + "p50": 6.704420040282551, + "p90": 6.716400699617259, + "p95": 6.718642043996769, + "p99": 6.720435119500378 + }, + "itl_ms": { + "mean": 6.7050363785128875, + "p50": 6.695530493743718, + "p90": 6.846846811822616, + "p95": 6.88849520374788, + "p99": 7.007950085680932 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_1024_2048.jsonl" + }, + { + "name": "c128_i1024_o2048", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 2048, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 133.46989706001477, + "request_throughput": 4.7950887360932315, + "input_token_throughput": 2508.84287300703, + "output_token_throughput": 4871.12086186491, + "total_token_throughput": 7379.96373487194, + "total_input_tokens": 334855, + "total_output_tokens": 650148, + "e2e_ms": { + "mean": 23639.356331531737, + "p50": 23619.91920748551, + "p90": 41096.837318109465, + "p95": 44752.062044409104, + "p99": 48201.59040482453 + }, + "ttft_ms": { + "mean": 198.2606400615623, + "p50": 102.33299050014466, + "p90": 570.831106393598, + "p95": 746.0507048497675, + "p99": 761.6026770081954 + }, + "tpot_ms": { + "mean": 23.365234939241812, + "p50": 23.89083861284945, + "p90": 24.153373456672526, + "p95": 24.25965965126051, + "p99": 24.887882278820108 + }, + "itl_ms": { + "mean": 23.115038657840238, + "p50": 22.805721484473906, + "p90": 25.43376050016377, + "p95": 32.6996164949378, + "p99": 36.15239749342436 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_128_1024_2048.jsonl" + }, + { + "name": "c1_i1024_o4096", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1024, + "output_len": 4096, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 79.46116249699844, + "request_throughput": 0.0629238214352687, + "input_token_throughput": 22.375710902381552, + "output_token_throughput": 148.13526042290957, + "total_token_throughput": 170.51097132529114, + "total_input_tokens": 1778, + "total_output_tokens": 11771, + "e2e_ms": { + "mean": 15890.771754994057, + "p50": 14598.433314997237, + "p90": 23686.08512879, + "p95": 24601.027589384466, + "p99": 25332.98155786004 + }, + "ttft_ms": { + "mean": 42.12920940481126, + "p50": 41.481438995106146, + "p90": 45.4949876118917, + "p95": 46.59649881650694, + "p99": 47.477707780199125 + }, + "tpot_ms": { + "mean": 6.725161891015255, + "p50": 6.712620497455561, + "p90": 6.755732904352653, + "p95": 6.7565145338363335, + "p99": 6.757139837423277 + }, + "itl_ms": { + "mean": 6.734912228627602, + "p50": 6.72975298948586, + "p90": 6.884617512696423, + "p95": 6.931063246156555, + "p99": 7.00651356310118 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_1024_4096.jsonl" + }, + { + "name": "c128_i1024_o4096", + "config": { + "phase": "main", + "concurrency": 128, + "input_len": 1024, + "output_len": 4096, + "dataset": "random", + "num_prompts": 640 + }, + "metrics": { + "success": 640, + "failed": 0, + "duration_s": 275.08098518897896, + "request_throughput": 2.3265875667862828, + "input_token_throughput": 1217.2960619940948, + "output_token_throughput": 4775.684510136155, + "total_token_throughput": 5992.98057213025, + "total_input_tokens": 334855, + "total_output_tokens": 1313700, + "e2e_ms": { + "mean": 48923.094904336176, + "p50": 49395.30037200893, + "p90": 86516.55968841516, + "p95": 92762.86578539002, + "p99": 97316.79100864421 + }, + "ttft_ms": { + "mean": 218.43703098265905, + "p50": 147.93294100672938, + "p90": 567.803863005247, + "p95": 736.089210139471, + "p99": 756.6278313548537 + }, + "tpot_ms": { + "mean": 23.993136593347142, + "p50": 24.11520213519814, + "p90": 25.682799309682903, + "p95": 25.924939912533848, + "p99": 26.623839328782584 + }, + "itl_ms": { + "mean": 23.753848993227077, + "p50": 22.822784987511113, + "p90": 24.192147998837754, + "p95": 27.596254809759543, + "p99": 86.22891287785025 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_128_1024_4096.jsonl" + }, + { + "name": "c1_i4096_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.0854074439848773, + "request_throughput": 1.6205315151318818, + "input_token_throughput": 3231.3398411729722, + "output_token_throughput": 122.83628884699664, + "total_token_throughput": 3354.176130019969, + "total_input_tokens": 9970, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 615.6534888024908, + "p50": 561.0614480101503, + "p90": 873.1742330011912, + "p95": 898.1507350050379, + "p99": 918.1319366081152 + }, + "ttft_ms": { + "mean": 113.27877099392936, + "p50": 114.13994699250907, + "p90": 140.1475009857677, + "p95": 148.5101829865016, + "p99": 155.20032858708873 + }, + "tpot_ms": { + "mean": 6.7182663676562875, + "p50": 6.7081030413473774, + "p90": 6.739791897229386, + "p95": 6.740897068400767, + "p99": 6.741781205337871 + }, + "itl_ms": { + "mean": 6.715573219334667, + "p50": 6.7164640058763325, + "p90": 6.88778919284232, + "p95": 6.937314548122231, + "p99": 7.244373657449614 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_4096_128.jsonl" + }, + { + "name": "c64_i4096_o128", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 128, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 27.099694294010988, + "request_throughput": 11.80825128609365, + "input_token_throughput": 24931.535856820174, + "output_token_throughput": 772.9238482453675, + "total_token_throughput": 25704.459705065543, + "total_input_tokens": 675637, + "total_output_tokens": 20946, + "e2e_ms": { + "mean": 5252.685820971146, + "p50": 4714.832158992067, + "p90": 9597.868900399773, + "p95": 10435.22773818986, + "p99": 11989.513149040287 + }, + "ttft_ms": { + "mean": 705.8739211091961, + "p50": 366.5684799925657, + "p90": 2010.9284130943706, + "p95": 2978.274026054715, + "p99": 3725.2794846516917 + }, + "tpot_ms": { + "mean": 76.32340626525998, + "p50": 76.2943883227518, + "p90": 96.5839731860407, + "p95": 108.06964486550896, + "p99": 233.29262652507254 + }, + "itl_ms": { + "mean": 70.56425622449346, + "p50": 16.781184007413685, + "p90": 198.48385320510718, + "p95": 248.3880425861571, + "p99": 256.2605793023249 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": false, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_64_4096_128.jsonl" + }, + { + "name": "c1_i4096_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.658745035994798, + "request_throughput": 1.366588803212553, + "input_token_throughput": 2724.9780736058306, + "output_token_throughput": 138.57210464575286, + "total_token_throughput": 2863.5501782515835, + "total_input_tokens": 9970, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 731.1363978078589, + "p50": 731.1096460034605, + "p90": 1146.9773760065436, + "p95": 1243.268521002028, + "p99": 1320.3014369984155 + }, + "ttft_ms": { + "mean": 54.709906002972275, + "p50": 47.65253601362929, + "p90": 66.72574519761838, + "p95": 67.17990359757096, + "p99": 67.54323031753302 + }, + "tpot_ms": { + "mean": 6.727269818785986, + "p50": 6.707462650956586, + "p90": 6.764210822905439, + "p95": 6.77092561357972, + "p99": 6.776297446119144 + }, + "itl_ms": { + "mean": 6.737199599670981, + "p50": 6.741824996424839, + "p90": 6.881189302657731, + "p95": 6.924558590981178, + "p99": 7.134522728447337 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_4096_256.jsonl" + }, + { + "name": "c64_i4096_o256", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 256, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 16.449123202008195, + "request_throughput": 19.453924447531204, + "input_token_throughput": 41074.3473498645, + "output_token_throughput": 2518.4321067607116, + "total_token_throughput": 43592.77945662521, + "total_input_tokens": 675637, + "total_output_tokens": 41426, + "e2e_ms": { + "mean": 2990.6639760214603, + "p50": 2892.804385002819, + "p90": 5216.253019598664, + "p95": 5802.251851401526, + "p99": 6644.63413677091 + }, + "ttft_ms": { + "mean": 216.46908835318754, + "p50": 120.06344750989228, + "p90": 605.4238382988842, + "p95": 804.2780677453267, + "p99": 815.3280701686163 + }, + "tpot_ms": { + "mean": 22.251804362551017, + "p50": 21.73764368671982, + "p90": 24.98197791283019, + "p95": 25.87954078425632, + "p99": 28.534352022444544 + }, + "itl_ms": { + "mean": 21.710834613935567, + "p50": 16.339479014277458, + "p90": 35.72288859868423, + "p95": 47.24770099273881, + "p99": 85.45168400160037 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_64_4096_256.jsonl" + }, + { + "name": "c1_i4096_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.6594501009967644, + "request_throughput": 1.3663255030142631, + "input_token_throughput": 2724.4530530104407, + "output_token_throughput": 138.54540600564627, + "total_token_throughput": 2862.998459016087, + "total_input_tokens": 9970, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 730.5364638043102, + "p50": 730.989553994732, + "p90": 1147.649170004297, + "p95": 1243.7729350000152, + "p99": 1320.6719469965901 + }, + "ttft_ms": { + "mean": 53.851668402785435, + "p50": 47.597177006537095, + "p90": 64.02949960320257, + "p95": 64.626579801552, + "p99": 65.10424396023154 + }, + "tpot_ms": { + "mean": 6.728677737284085, + "p50": 6.708104942236404, + "p90": 6.770449891860923, + "p95": 6.7753128182598035, + "p99": 6.779203159378907 + }, + "itl_ms": { + "mean": 6.73937784067023, + "p50": 6.737591014825739, + "p90": 6.900259788380936, + "p95": 6.942523361067288, + "p99": 7.090970962017309 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_4096_512.jsonl" + }, + { + "name": "c64_i4096_o512", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 512, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 27.31912976797321, + "request_throughput": 11.713403857217397, + "input_token_throughput": 24731.27825587122, + "output_token_throughput": 3100.0255395866916, + "total_token_throughput": 27831.303795457912, + "total_input_tokens": 675637, + "total_output_tokens": 84690, + "e2e_ms": { + "mean": 4860.531406028804, + "p50": 4964.397494011791, + "p90": 8671.064496890176, + "p95": 9051.41342166462, + "p99": 9668.73572528013 + }, + "ttft_ms": { + "mean": 174.8319179313512, + "p50": 100.47747699718457, + "p90": 527.0181634987239, + "p95": 584.906001255149, + "p99": 601.9537152591511 + }, + "tpot_ms": { + "mean": 17.82869827666415, + "p50": 18.254847125018177, + "p90": 18.573381245585715, + "p95": 18.777003847560263, + "p99": 19.951478950302665 + }, + "itl_ms": { + "mean": 17.790459763842904, + "p50": 16.201541511691175, + "p90": 27.450341390795074, + "p95": 31.0013980633812, + "p99": 36.46449689462316 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_64_4096_512.jsonl" + }, + { + "name": "c1_i4096_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 10.57582659801119, + "request_throughput": 0.4727762840722315, + "input_token_throughput": 942.7159104400296, + "output_token_throughput": 144.76409818291728, + "total_token_throughput": 1087.4800086229468, + "total_input_tokens": 9970, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 2113.7520164076705, + "p50": 858.8050559919793, + "p90": 4557.140987808816, + "p95": 4687.4714534089435, + "p99": 4791.735825889045 + }, + "ttft_ms": { + "mean": 54.499105404829606, + "p50": 47.3600749974139, + "p90": 66.29754161695018, + "p95": 66.58417182043195, + "p99": 66.81347598321736 + }, + "tpot_ms": { + "mean": 6.734874706680725, + "p50": 6.722214550245553, + "p90": 6.772506061471742, + "p95": 6.78079893645199, + "p99": 6.787433236436187 + }, + "itl_ms": { + "mean": 6.747072798838939, + "p50": 6.746081984601915, + "p90": 6.896372506162152, + "p95": 6.942834756046068, + "p99": 7.040538992441725 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_4096_1024.jsonl" + }, + { + "name": "c64_i4096_o1024", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 1024, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 52.138183050992666, + "request_throughput": 6.137536470863027, + "input_token_throughput": 12958.583526764009, + "output_token_throughput": 3283.927248338205, + "total_token_throughput": 16242.510775102213, + "total_input_tokens": 675637, + "total_output_tokens": 171218, + "e2e_ms": { + "mean": 9239.511910518468, + "p50": 9612.64459049562, + "p90": 16225.299288914539, + "p95": 17164.766070038608, + "p99": 17906.819723816297 + }, + "ttft_ms": { + "mean": 197.14426652762995, + "p50": 96.6091855079867, + "p90": 756.5386313915951, + "p95": 789.7942044000956, + "p99": 800.0755239935825 + }, + "tpot_ms": { + "mean": 17.056337422967584, + "p50": 17.351856994488298, + "p90": 17.638552956453005, + "p95": 17.951327604176846, + "p99": 19.325315261683347 + }, + "itl_ms": { + "mean": 16.95405888753211, + "p50": 16.254876492894255, + "p90": 19.355191584327265, + "p95": 27.920874397386786, + "p99": 34.48984432354336 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_64_4096_1024.jsonl" + }, + { + "name": "c1_i4096_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 38.30321971999365, + "request_throughput": 0.1305373291475568, + "input_token_throughput": 260.2914343202283, + "output_token_throughput": 146.90671022266045, + "total_token_throughput": 407.1981445428887, + "total_input_tokens": 9970, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 7659.171856596367, + "p50": 7501.7676659917925, + "p90": 11512.226327991812, + "p95": 11647.121157991933, + "p99": 11755.03702199203 + }, + "ttft_ms": { + "mean": 55.00147619750351, + "p50": 47.79739800142124, + "p90": 66.96408639545552, + "p95": 67.21895219525322, + "p99": 67.42284483509138 + }, + "tpot_ms": { + "mean": 6.749552102034963, + "p50": 6.751980732594644, + "p90": 6.793154116167625, + "p95": 6.794435671481723, + "p99": 6.795460915733 + }, + "itl_ms": { + "mean": 6.762827909467697, + "p50": 6.759966490790248, + "p90": 6.9036511005833745, + "p95": 6.945121941680554, + "p99": 7.021578256681096 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_4096_2048.jsonl" + }, + { + "name": "c64_i4096_o2048", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 2048, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 97.68905732702115, + "request_throughput": 3.2756995384731473, + "input_token_throughput": 6916.199403360568, + "output_token_throughput": 3408.877197834196, + "total_token_throughput": 10325.076601194765, + "total_input_tokens": 675637, + "total_output_tokens": 333010, + "e2e_ms": { + "mean": 17265.869403236684, + "p50": 16820.79488999443, + "p90": 31243.420736011474, + "p95": 32918.48102155491, + "p99": 34336.54211862915 + }, + "ttft_ms": { + "mean": 162.13746994908433, + "p50": 91.81087499018759, + "p90": 534.6608572959667, + "p95": 570.7538236456458, + "p99": 582.0342552423244 + }, + "tpot_ms": { + "mean": 16.564744187293176, + "p50": 16.84016802253919, + "p90": 16.97582263718213, + "p95": 17.058498259752593, + "p99": 18.073979461173185 + }, + "itl_ms": { + "mean": 16.45873048013487, + "p50": 16.287181002553552, + "p90": 17.15008311439306, + "p95": 20.545937879069243, + "p99": 31.291485934634682 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_64_4096_2048.jsonl" + }, + { + "name": "c1_i4096_o4096", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 4096, + "output_len": 4096, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 79.97539899300318, + "request_throughput": 0.06251922544878376, + "input_token_throughput": 124.66333554487483, + "output_token_throughput": 147.18276055152674, + "total_token_throughput": 271.84609609640154, + "total_input_tokens": 9970, + "total_output_tokens": 11771, + "e2e_ms": { + "mean": 15993.579583399696, + "p50": 14702.334433008218, + "p90": 23806.792291003512, + "p95": 24761.64468100178, + "p99": 25525.526593000395 + }, + "ttft_ms": { + "mean": 55.41398960631341, + "p50": 48.41957500320859, + "p90": 66.52183539699763, + "p95": 66.70366719481535, + "p99": 66.84913263306953 + }, + "tpot_ms": { + "mean": 6.770702241974898, + "p50": 6.757647574057017, + "p90": 6.794975151768566, + "p95": 6.7974891098195185, + "p99": 6.7995002762602805 + }, + "itl_ms": { + "mean": 6.772954078104776, + "p50": 6.770955995307304, + "p90": 6.9077145017217845, + "p95": 6.949156500922982, + "p99": 7.023812456463929 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_4096_4096.jsonl" + }, + { + "name": "c64_i4096_o4096", + "config": { + "phase": "main", + "concurrency": 64, + "input_len": 4096, + "output_len": 4096, + "dataset": "random", + "num_prompts": 320 + }, + "metrics": { + "success": 320, + "failed": 0, + "duration_s": 192.00843709899345, + "request_throughput": 1.6665934311783297, + "input_token_throughput": 3518.7880814407285, + "output_token_throughput": 3408.9439500126596, + "total_token_throughput": 6927.732031453388, + "total_input_tokens": 675637, + "total_output_tokens": 654546, + "e2e_ms": { + "mean": 33560.76050478714, + "p50": 33245.46831249609, + "p90": 59875.34798151173, + "p95": 65515.45453574946, + "p99": 68183.66740680416 + }, + "ttft_ms": { + "mean": 163.8100891470458, + "p50": 90.77135000552516, + "p90": 516.3448837934993, + "p95": 576.4098760992056, + "p99": 599.0004324031179 + }, + "tpot_ms": { + "mean": 16.438118558644927, + "p50": 16.6576844549002, + "p90": 16.753551188242543, + "p95": 16.788353501190862, + "p99": 16.975070930319287 + }, + "itl_ms": { + "mean": 16.346701673086326, + "p50": 16.38738051406108, + "p90": 16.858579698600806, + "p95": 17.46838169492548, + "p99": 29.494421854615243 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_64_4096_4096.jsonl" + }, + { + "name": "c1_i16384_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.7416468400042504, + "request_throughput": 1.3363099762762003, + "input_token_throughput": 11422.243153218451, + "output_token_throughput": 101.292296201736, + "total_token_throughput": 11523.535449420186, + "total_input_tokens": 42738, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 746.9622810021974, + "p50": 793.1687289965339, + "p90": 1112.0859866088722, + "p95": 1184.4593688088933, + "p99": 1242.3580745689105 + }, + "ttft_ms": { + "mean": 244.24475480336696, + "p50": 203.74058501329273, + "p90": 424.9969316122588, + "p95": 433.33762081456365, + "p99": 440.01017217640765 + }, + "tpot_ms": { + "mean": 6.720416888255487, + "p50": 6.736813561917737, + "p90": 6.792966854380781, + "p95": 6.798383077097527, + "p99": 6.802716055270923 + }, + "itl_ms": { + "mean": 6.738215297567921, + "p50": 6.794262997573242, + "p90": 6.934145401464775, + "p95": 6.970913801342249, + "p99": 7.334358422085639 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_16384_128.jsonl" + }, + { + "name": "c32_i16384_o128", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 128, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 29.665646167995874, + "request_throughput": 5.3934439551366475, + "input_token_throughput": 43522.36228695046, + "output_token_throughput": 356.16955518733636, + "total_token_throughput": 43878.531842137796, + "total_input_tokens": 1291119, + "total_output_tokens": 10566, + "e2e_ms": { + "mean": 5789.677598388153, + "p50": 5906.899729496217, + "p90": 9852.575152096688, + "p95": 10661.965765064811, + "p99": 11830.348544723525 + }, + "ttft_ms": { + "mean": 996.1798031064973, + "p50": 711.6568210039986, + "p90": 2225.204480701359, + "p95": 3789.3565844627938, + "p99": 4532.54993600538 + }, + "tpot_ms": { + "mean": 78.85899350592113, + "p50": 76.84775757399144, + "p90": 116.30529798200597, + "p95": 150.73226668917212, + "p99": 226.61302751671002 + }, + "itl_ms": { + "mean": 74.18084010396575, + "p50": 13.344642997253686, + "p90": 252.1555712155532, + "p95": 263.4294065006543, + "p99": 274.03829396585934 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_32_16384_128.jsonl" + }, + { + "name": "c1_i16384_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.8248532990110107, + "request_throughput": 1.307239679308183, + "input_token_throughput": 11173.761882854626, + "output_token_throughput": 132.55410348184978, + "total_token_throughput": 11306.315986336476, + "total_input_tokens": 42738, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 763.5138192039449, + "p50": 759.5113300194498, + "p90": 1207.4323965993246, + "p95": 1299.0657877991907, + "p99": 1372.3725007590838 + }, + "ttft_ms": { + "mean": 87.44428500649519, + "p50": 80.63636301085353, + "p90": 121.7506884073373, + "p95": 122.3494662088342, + "p99": 122.82848845003173 + }, + "tpot_ms": { + "mean": 6.727216758879248, + "p50": 6.71551957022214, + "p90": 6.754395038357036, + "p95": 6.758074705418023, + "p99": 6.761018439066813 + }, + "itl_ms": { + "mean": 6.746741532935517, + "p50": 6.7992639960721135, + "p90": 6.96806499036029, + "p95": 7.014268980128691, + "p99": 7.566279004095122 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_16384_256.jsonl" + }, + { + "name": "c32_i16384_o256", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 256, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 12.461962151981425, + "request_throughput": 12.839069646392751, + "input_token_throughput": 103604.79226738102, + "output_token_throughput": 1782.5443320310537, + "total_token_throughput": 105387.33659941207, + "total_input_tokens": 1291119, + "total_output_tokens": 22214, + "e2e_ms": { + "mean": 2229.4527406438647, + "p50": 2167.282502487069, + "p90": 3691.0632932878793, + "p95": 3832.958550745388, + "p99": 4262.988245337619 + }, + "ttft_ms": { + "mean": 200.0951993633862, + "p50": 141.25127698935103, + "p90": 556.7186772095738, + "p95": 636.4848169992911, + "p99": 644.9647748749703 + }, + "tpot_ms": { + "mean": 14.839397661739069, + "p50": 15.014273620808723, + "p90": 16.209308889668645, + "p95": 16.944263605099696, + "p99": 20.775335025510376 + }, + "itl_ms": { + "mean": 15.171862422589003, + "p50": 12.557223002659157, + "p90": 31.59359798883088, + "p95": 37.34407600131817, + "p99": 48.670664022210985 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_32_16384_256.jsonl" + }, + { + "name": "c1_i16384_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 3.8126014840090647, + "request_throughput": 1.3114405009207388, + "input_token_throughput": 11209.668825670107, + "output_token_throughput": 132.9800667933629, + "total_token_throughput": 11342.64889246347, + "total_input_tokens": 42738, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 761.1607200058643, + "p50": 758.4194740047678, + "p90": 1202.8484933951404, + "p95": 1293.046706187306, + "p99": 1365.2052764210384 + }, + "ttft_ms": { + "mean": 85.19858720246702, + "p50": 78.2607370056212, + "p90": 117.92198420735076, + "p95": 118.64809161052108, + "p99": 119.22897753305733 + }, + "tpot_ms": { + "mean": 6.726653841894257, + "p50": 6.718013685991341, + "p90": 6.75291219102312, + "p95": 6.756540267141408, + "p99": 6.759442728036039 + }, + "itl_ms": { + "mean": 6.745665610796714, + "p50": 6.799466005759314, + "p90": 7.004150975262746, + "p95": 7.096040004398674, + "p99": 7.3483510059304535 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_16384_512.jsonl" + }, + { + "name": "c32_i16384_o512", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 512, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 20.42796457701479, + "request_throughput": 7.832400501615778, + "input_token_throughput": 63203.50689528539, + "output_token_throughput": 1977.191601626633, + "total_token_throughput": 65180.698496912024, + "total_input_tokens": 1291119, + "total_output_tokens": 40390, + "e2e_ms": { + "mean": 3673.450332867833, + "p50": 3403.5250500019174, + "p90": 6646.781725299661, + "p95": 7038.214879437871, + "p99": 7504.8199216401545 + }, + "ttft_ms": { + "mean": 190.689647281215, + "p50": 130.69589500082657, + "p90": 422.3435439140301, + "p95": 640.862681595899, + "p99": 739.0641469051478 + }, + "tpot_ms": { + "mean": 14.041667680472107, + "p50": 14.111390889298962, + "p90": 14.77375568637589, + "p95": 15.699944199987575, + "p99": 18.530489535910686 + }, + "itl_ms": { + "mean": 14.017145062407957, + "p50": 12.583733012434095, + "p90": 24.489443507627584, + "p95": 33.16136909998022, + "p99": 42.72941159870243 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_32_16384_512.jsonl" + }, + { + "name": "c1_i16384_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 10.848079899995355, + "request_throughput": 0.4609110594771837, + "input_token_throughput": 3939.683371987175, + "output_token_throughput": 141.13096641191365, + "total_token_throughput": 4080.814338399089, + "total_input_tokens": 42738, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 2168.263963004574, + "p50": 934.9753590067849, + "p90": 4636.084477195982, + "p95": 4767.81152759795, + "p99": 4873.193167919526 + }, + "ttft_ms": { + "mean": 96.11712900805287, + "p50": 109.78887401870452, + "p90": 129.60210220771842, + "p95": 132.0783076051157, + "p99": 134.05927192303352 + }, + "tpot_ms": { + "mean": 6.752114930746313, + "p50": 6.729682338092817, + "p90": 6.801452364504652, + "p95": 6.804286228679045, + "p99": 6.806553320018559 + }, + "itl_ms": { + "mean": 6.798231347786077, + "p50": 6.802242991398089, + "p90": 6.969152204692364, + "p95": 7.020317575370427, + "p99": 7.177459584490862 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_16384_1024.jsonl" + }, + { + "name": "c32_i16384_o1024", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 1024, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 40.018767052009935, + "request_throughput": 3.9981241748916907, + "input_token_throughput": 32262.838041012405, + "output_token_throughput": 2122.3542416890677, + "total_token_throughput": 34385.19228270147, + "total_input_tokens": 1291119, + "total_output_tokens": 84934, + "e2e_ms": { + "mean": 7223.56558833817, + "p50": 7723.683465505019, + "p90": 12056.387461713166, + "p95": 13034.13519445021, + "p99": 13797.926251252065 + }, + "ttft_ms": { + "mean": 226.08372724425863, + "p50": 127.79736549418885, + "p90": 774.0484802838182, + "p95": 789.9365069199092, + "p99": 950.3970919386484 + }, + "tpot_ms": { + "mean": 13.375908518568897, + "p50": 13.288246175475457, + "p90": 13.820212318785108, + "p95": 14.232104893723827, + "p99": 22.015017151728067 + }, + "itl_ms": { + "mean": 13.27381102657931, + "p50": 12.61283500934951, + "p90": 13.946030507213436, + "p95": 22.966549753618892, + "p99": 39.84888230188517 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_32_16384_1024.jsonl" + }, + { + "name": "c1_i16384_o2048", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 16384, + "output_len": 2048, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 38.62168169600773, + "request_throughput": 0.12946096028016418, + "input_token_throughput": 1106.5805040907312, + "output_token_throughput": 145.69536469929676, + "total_token_throughput": 1252.275868790028, + "total_input_tokens": 42738, + "total_output_tokens": 5627, + "e2e_ms": { + "mean": 7722.665159997996, + "p50": 7533.396830986021, + "p90": 11619.30468720384, + "p95": 11757.026566605782, + "p99": 11867.204070127336 + }, + "ttft_ms": { + "mean": 92.6008160051424, + "p50": 91.59555900259875, + "p90": 129.70803180942312, + "p95": 132.64805141370744, + "p99": 135.0000670971349 + }, + "tpot_ms": { + "mean": 6.767648317537002, + "p50": 6.796165545190339, + "p90": 6.811977873980548, + "p95": 6.816418280084744, + "p99": 6.819970604968102 + }, + "itl_ms": { + "mean": 6.787064156022911, + "p50": 6.7920129804406315, + "p90": 6.940115010365844, + "p95": 6.9823910016566515, + "p99": 7.056562218349427 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_16384_2048.jsonl" + }, + { + "name": "c32_i16384_o2048", + "config": { + "phase": "main", + "concurrency": 32, + "input_len": 16384, + "output_len": 2048, + "dataset": "random", + "num_prompts": 160 + }, + "metrics": { + "success": 160, + "failed": 0, + "duration_s": 82.30778569099493, + "request_throughput": 1.9439230281407651, + "input_token_throughput": 15686.474726062977, + "output_token_throughput": 2226.2535489403595, + "total_token_throughput": 17912.728275003337, + "total_input_tokens": 1291119, + "total_output_tokens": 183238, + "e2e_ms": { + "mean": 14894.456553130476, + "p50": 15637.624575494556, + "p90": 23955.132565906384, + "p95": 25291.544086861537, + "p99": 26578.48927184241 + }, + "ttft_ms": { + "mean": 187.66604684860795, + "p50": 125.363400002243, + "p90": 419.96127700840566, + "p95": 628.0171468533806, + "p99": 806.2383803006377 + }, + "tpot_ms": { + "mean": 12.880386136891058, + "p50": 13.052008063056935, + "p90": 13.237517172090145, + "p95": 13.394617533097497, + "p99": 14.850997615043472 + }, + "itl_ms": { + "mean": 12.886822602987632, + "p50": 12.698767008259892, + "p90": 13.1840615067631, + "p95": 14.173676259815693, + "p99": 34.75605665880721 + }, + "gpu_memory": { + "peak_used_mb": 132932.0, + "avg_used_mb": 132932.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_32_16384_2048.jsonl" + }, + { + "name": "c1_i65536_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 5.979828148992965, + "request_throughput": 0.8361444301442051, + "input_token_throughput": 29066.05268067286, + "output_token_throughput": 63.37974780493075, + "total_token_throughput": 29129.43242847779, + "total_input_tokens": 173810, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 1194.5084626029711, + "p50": 717.2065060003661, + "p90": 2381.096083810553, + "p95": 2550.764347409131, + "p99": 2686.4989582879934 + }, + "ttft_ms": { + "mean": 697.6236455957405, + "p50": 247.50089697772637, + "p90": 1633.7114335969093, + "p95": 1783.813636796549, + "p99": 1903.895399356261 + }, + "tpot_ms": { + "mean": 6.668602271081101, + "p50": 6.7253280998556875, + "p90": 6.751154703156585, + "p95": 6.75149141538628, + "p99": 6.7517607851700365 + }, + "itl_ms": { + "mean": 6.824716656570512, + "p50": 6.875582999782637, + "p90": 7.054750301176682, + "p95": 7.115953753236681, + "p99": 7.555937078141144 + }, + "gpu_memory": { + "peak_used_mb": 133260.0, + "avg_used_mb": 133009.68421052632, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_65536_128.jsonl" + }, + { + "name": "c8_i65536_o128", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 128, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 39.645488456008025, + "request_throughput": 1.0089420400100595, + "input_token_throughput": 37118.27139254208, + "output_token_throughput": 64.77407896864582, + "total_token_throughput": 37183.045471510726, + "total_input_tokens": 1471572, + "total_output_tokens": 2568, + "e2e_ms": { + "mean": 7821.816953149391, + "p50": 7532.596676493995, + "p90": 14040.57804098993, + "p95": 14289.917052967932, + "p99": 16484.16690281534 + }, + "ttft_ms": { + "mean": 3209.808414100553, + "p50": 2829.1647829901194, + "p90": 5736.555838398636, + "p95": 7445.337255309275, + "p99": 8645.530720362147 + }, + "tpot_ms": { + "mean": 88.42192167431719, + "p50": 79.14389640022598, + "p90": 163.34168494834844, + "p95": 248.75438660297624, + "p99": 263.8012609491124 + }, + "itl_ms": { + "mean": 83.73990312849202, + "p50": 8.835267013637349, + "p90": 285.96494658268057, + "p95": 294.62111500033643, + "p99": 342.85850628395565 + }, + "gpu_memory": { + "peak_used_mb": 133780.0, + "avg_used_mb": 133307.27272727274, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": false, + "overall": "❌" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_8_65536_128.jsonl" + }, + { + "name": "c1_i65536_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.205351618991699, + "request_throughput": 1.1889612220342305, + "input_token_throughput": 41330.670000353915, + "output_token_throughput": 120.56066791427097, + "total_token_throughput": 41451.23066826819, + "total_input_tokens": 173810, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 839.7061410069, + "p50": 868.7234710087068, + "p90": 1248.29141360824, + "p95": 1306.3532338070215, + "p99": 1352.8026899660472 + }, + "ttft_ms": { + "mean": 161.62108960561454, + "p50": 179.29533100686967, + "p90": 252.30673381011005, + "p95": 254.46968341129832, + "p99": 256.20004309224896 + }, + "tpot_ms": { + "mean": 6.735750522493605, + "p50": 6.755977851234777, + "p90": 6.784939020019157, + "p95": 6.793552222764636, + "p99": 6.80044278496102 + }, + "itl_ms": { + "mean": 6.807582022121501, + "p50": 6.856819003587589, + "p90": 7.1003060875227675, + "p95": 7.191569736460224, + "p99": 7.500103442289398 + }, + "gpu_memory": { + "peak_used_mb": 133780.0, + "avg_used_mb": 133780.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_65536_256.jsonl" + }, + { + "name": "c8_i65536_o256", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 256, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 8.643470701994374, + "request_throughput": 4.627770646665175, + "input_token_throughput": 170252.44265135913, + "output_token_throughput": 608.089062971804, + "total_token_throughput": 170860.53171433092, + "total_input_tokens": 1471572, + "total_output_tokens": 5256, + "e2e_ms": { + "mean": 1581.5019286506868, + "p50": 1422.0479399955366, + "p90": 2723.607920407085, + "p95": 2865.085011156043, + "p99": 2998.3723240473773 + }, + "ttft_ms": { + "mean": 356.03623832575977, + "p50": 322.12173151492607, + "p90": 653.8560661108933, + "p95": 749.1073189507006, + "p99": 864.765941716323 + }, + "tpot_ms": { + "mean": 9.142763488004903, + "p50": 9.527620677225901, + "p90": 10.037834474508111, + "p95": 10.212376501737555, + "p99": 10.296325263987136 + }, + "itl_ms": { + "mean": 11.325642503234223, + "p50": 8.695702519617043, + "p90": 15.801905601983892, + "p95": 25.98413567902753, + "p99": 93.4788243641378 + }, + "gpu_memory": { + "peak_used_mb": 133780.0, + "avg_used_mb": 133780.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_8_65536_256.jsonl" + }, + { + "name": "c1_i65536_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.22689065898885, + "request_throughput": 1.182902611726439, + "input_token_throughput": 41120.06058883447, + "output_token_throughput": 119.94632482906093, + "total_token_throughput": 41240.006913663536, + "total_input_tokens": 173810, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 843.982104404131, + "p50": 873.4139300067909, + "p90": 1252.0642684074119, + "p95": 1310.3560922085308, + "p99": 1356.9895512494259 + }, + "ttft_ms": { + "mean": 184.7932830103673, + "p50": 207.99873900250532, + "p90": 287.43030800833367, + "p95": 288.96910000476055, + "p99": 290.20013360190205 + }, + "tpot_ms": { + "mean": 6.539759853660324, + "p50": 6.52367834317927, + "p90": 6.738242484397563, + "p95": 6.744176779429061, + "p99": 6.748924215454261 + }, + "itl_ms": { + "mean": 6.809284541349904, + "p50": 6.858499997179024, + "p90": 7.103115899371915, + "p95": 7.176107993291225, + "p99": 7.463799362885767 + }, + "gpu_memory": { + "peak_used_mb": 133780.0, + "avg_used_mb": 133780.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_65536_512.jsonl" + }, + { + "name": "c8_i65536_o512", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 512, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 15.791608511004597, + "request_throughput": 2.5329908585389167, + "input_token_throughput": 93186.96059204577, + "output_token_throughput": 705.6912531889423, + "total_token_throughput": 93892.65184523471, + "total_input_tokens": 1471572, + "total_output_tokens": 11144, + "e2e_ms": { + "mean": 2813.447674074996, + "p50": 3025.5881055054488, + "p90": 4910.965449296054, + "p95": 5054.251725919312, + "p99": 5200.705566430115 + }, + "ttft_ms": { + "mean": 274.49545034905896, + "p50": 277.5276810134528, + "p90": 459.80448708287463, + "p95": 661.3905629361398, + "p99": 679.1221809445415 + }, + "tpot_ms": { + "mean": 9.104545633011229, + "p50": 9.216829093139399, + "p90": 9.54288235983806, + "p95": 9.628486301198969, + "p99": 10.393052560959216 + }, + "itl_ms": { + "mean": 10.05413049895824, + "p50": 8.68834598804824, + "p90": 10.545664001256227, + "p95": 16.518691991223022, + "p99": 69.51865501469001 + }, + "gpu_memory": { + "peak_used_mb": 133780.0, + "avg_used_mb": 133780.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_8_65536_512.jsonl" + }, + { + "name": "c1_i65536_o1024", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 65536, + "output_len": 1024, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 11.221458473999519, + "request_throughput": 0.44557487884352653, + "input_token_throughput": 15489.07393835867, + "output_token_throughput": 136.43502790188782, + "total_token_throughput": 15625.508966260559, + "total_input_tokens": 173810, + "total_output_tokens": 1531, + "e2e_ms": { + "mean": 2242.899997602217, + "p50": 1069.672420999268, + "p90": 4670.665889407974, + "p95": 4765.812398202252, + "p99": 4841.929605237674 + }, + "ttft_ms": { + "mean": 161.17175800609402, + "p50": 174.0668680286035, + "p90": 253.8997896015644, + "p95": 254.4195618014783, + "p99": 254.83537956140933 + }, + "tpot_ms": { + "mean": 6.757404848240741, + "p50": 6.754809487582192, + "p90": 6.844067327086863, + "p95": 6.851316639924977, + "p99": 6.857116090195467 + }, + "itl_ms": { + "mean": 6.8386421748008654, + "p50": 6.861203015432693, + "p90": 7.040805980795994, + "p95": 7.1101105568232015, + "p99": 7.256177014496642 + }, + "gpu_memory": { + "peak_used_mb": 133780.0, + "avg_used_mb": 133780.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_65536_1024.jsonl" + }, + { + "name": "c8_i65536_o1024", + "config": { + "phase": "main", + "concurrency": 8, + "input_len": 65536, + "output_len": 1024, + "dataset": "random", + "num_prompts": 40 + }, + "metrics": { + "success": 40, + "failed": 0, + "duration_s": 29.799556770012714, + "request_throughput": 1.3423018439070205, + "input_token_throughput": 49382.34522604855, + "output_token_throughput": 734.776029354703, + "total_token_throughput": 50117.121255403246, + "total_input_tokens": 1471572, + "total_output_tokens": 21896, + "e2e_ms": { + "mean": 5146.086770098918, + "p50": 5226.150454007438, + "p90": 8645.80303388648, + "p95": 8994.806143906315, + "p99": 9476.986618578085 + }, + "ttft_ms": { + "mean": 281.65961030026665, + "p50": 266.0276324895676, + "p90": 418.90704880934237, + "p95": 671.0752429964487, + "p99": 707.7661068245652 + }, + "tpot_ms": { + "mean": 8.906683843567604, + "p50": 8.975047370547262, + "p90": 9.154302167481521, + "p95": 9.196039805515325, + "p99": 10.493496254532058 + }, + "itl_ms": { + "mean": 9.247891059879954, + "p50": 8.68852600979153, + "p90": 8.970274080638774, + "p95": 11.745035581407134, + "p99": 36.71318077569595 + }, + "gpu_memory": { + "peak_used_mb": 133780.0, + "avg_used_mb": 133780.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_8_65536_1024.jsonl" + }, + { + "name": "c1_i131072_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 9.016311184008373, + "request_throughput": 0.5545505138363198, + "input_token_throughput": 41083.09844684438, + "output_token_throughput": 42.03492894879304, + "total_token_throughput": 41125.13337579317, + "total_input_tokens": 370418, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 1801.840906200232, + "p50": 962.3327779991087, + "p90": 3719.553761993302, + "p95": 3782.0753349922597, + "p99": 3832.092593391426 + }, + "ttft_ms": { + "mean": 1332.752106199041, + "p50": 549.2673270055093, + "p90": 3005.3896251891274, + "p95": 3042.4025475862436, + "p99": 3072.0128855039366 + }, + "tpot_ms": { + "mean": 6.340339875959231, + "p50": 6.323813537255022, + "p90": 6.668300853925757, + "p95": 6.696194727555849, + "p99": 6.718509826459921 + }, + "itl_ms": { + "mean": 6.877446249284429, + "p50": 6.9577679969370365, + "p90": 7.167970004957169, + "p95": 7.233284006360918, + "p99": 8.599375199992219 + }, + "gpu_memory": { + "peak_used_mb": 133780.0, + "avg_used_mb": 133780.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_131072_128.jsonl" + }, + { + "name": "c4_i131072_o128", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 128, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 24.360167828010162, + "request_throughput": 0.8210124060394736, + "input_token_throughput": 60525.075623850295, + "output_token_throughput": 46.75665652394802, + "total_token_throughput": 60571.83228037424, + "total_input_tokens": 1474401, + "total_output_tokens": 1139, + "e2e_ms": { + "mean": 4786.172839647043, + "p50": 5626.231432994246, + "p90": 8825.416628399398, + "p95": 9054.740018452867, + "p99": 9263.157454879838 + }, + "ttft_ms": { + "mean": 2268.90818515094, + "p50": 1815.796633993159, + "p90": 5463.91780730628, + "p95": 5665.4495449300175, + "p99": 7563.445302569886 + }, + "tpot_ms": { + "mean": 46.91910022441427, + "p50": 8.155252634180076, + "p90": 111.22875968014293, + "p95": 130.55081088415008, + "p99": 135.39232037676058 + }, + "itl_ms": { + "mean": 60.29291451981146, + "p50": 7.773411023663357, + "p90": 318.7832578085363, + "p95": 342.509480001172, + "p99": 410.38581036787946 + }, + "gpu_memory": { + "peak_used_mb": 134302.0, + "avg_used_mb": 134005.17647058822, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_4_131072_128.jsonl" + }, + { + "name": "c1_i131072_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.8524470679985825, + "request_throughput": 1.030407942618172, + "input_token_throughput": 76336.32985774761, + "output_token_throughput": 104.48336538148263, + "total_token_throughput": 76440.81322312908, + "total_input_tokens": 370418, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 969.0659300016705, + "p50": 1085.9827550011687, + "p90": 1327.6738234155346, + "p95": 1348.4903072181623, + "p99": 1365.1434942602646 + }, + "ttft_ms": { + "mean": 324.2844178050291, + "p50": 446.85381901217625, + "p90": 519.0396234043874, + "p95": 526.125369197689, + "p99": 531.7939658323303 + }, + "tpot_ms": { + "mean": 6.38195852240975, + "p50": 6.3424957519270135, + "p90": 6.734525240305068, + "p95": 6.740891553716675, + "p99": 6.745984604445959 + }, + "itl_ms": { + "mean": 6.873506368875111, + "p50": 6.902034016093239, + "p90": 7.1110547869466245, + "p95": 7.182737207040191, + "p99": 8.356347646331415 + }, + "gpu_memory": { + "peak_used_mb": 134302.0, + "avg_used_mb": 134302.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_131072_256.jsonl" + }, + { + "name": "c4_i131072_o256", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 256, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 8.323286791011924, + "request_throughput": 2.402896896643934, + "input_token_throughput": 177141.67936543564, + "output_token_throughput": 306.008919787605, + "total_token_throughput": 177447.68828522324, + "total_input_tokens": 1474401, + "total_output_tokens": 2547, + "e2e_ms": { + "mean": 1532.3867275510565, + "p50": 1609.7988390101818, + "p90": 2462.9763679899047, + "p95": 2573.004158611002, + "p99": 2602.991411728144 + }, + "ttft_ms": { + "mean": 542.0563667998067, + "p50": 561.1400620109634, + "p90": 786.9597911747405, + "p95": 826.1095973968623, + "p99": 873.837375488656 + }, + "tpot_ms": { + "mean": 7.110337367266883, + "p50": 7.7316950582082455, + "p90": 8.280846323565472, + "p95": 8.423364776975943, + "p99": 8.690418247445379 + }, + "itl_ms": { + "mean": 10.038461456174083, + "p50": 7.76114099426195, + "p90": 13.23855118243955, + "p95": 20.75249279732816, + "p99": 85.82791325403365 + }, + "gpu_memory": { + "peak_used_mb": 134302.0, + "avg_used_mb": 134302.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_4_131072_256.jsonl" + }, + { + "name": "c1_i131072_o512", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 131072, + "output_len": 512, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 4.870791513007134, + "request_throughput": 1.0265272054137038, + "input_token_throughput": 76048.83087498667, + "output_token_throughput": 104.08985862894957, + "total_token_throughput": 76152.92073361563, + "total_input_tokens": 370418, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 972.7444024058059, + "p50": 1082.7535319840536, + "p90": 1337.6641850161832, + "p95": 1353.217571019195, + "p99": 1365.6602798216045 + }, + "ttft_ms": { + "mean": 327.9147273977287, + "p50": 443.6211699794512, + "p90": 527.4083624070045, + "p95": 528.5839962074533, + "p99": 529.5245032478124 + }, + "tpot_ms": { + "mean": 6.384223606274097, + "p50": 6.339855917367684, + "p90": 6.738858764336018, + "p95": 6.743368868929076, + "p99": 6.746976952603522 + }, + "itl_ms": { + "mean": 6.8740309701973334, + "p50": 6.8926950043533, + "p90": 7.111179392086342, + "p95": 7.18118479126133, + "p99": 8.424099116818978 + }, + "gpu_memory": { + "peak_used_mb": 134302.0, + "avg_used_mb": 134302.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_131072_512.jsonl" + }, + { + "name": "c4_i131072_o512", + "config": { + "phase": "main", + "concurrency": 4, + "input_len": 131072, + "output_len": 512, + "dataset": "random", + "num_prompts": 20 + }, + "metrics": { + "success": 20, + "failed": 0, + "duration_s": 15.363296866009478, + "request_throughput": 1.3018039145132316, + "input_token_throughput": 95969.04966811115, + "output_token_throughput": 382.40489988826175, + "total_token_throughput": 96351.45456799942, + "total_input_tokens": 1474401, + "total_output_tokens": 5875, + "e2e_ms": { + "mean": 2674.266563852143, + "p50": 2755.7085349981207, + "p90": 3774.087236606283, + "p95": 3889.944781288796, + "p99": 4365.159926651103 + }, + "ttft_ms": { + "mean": 384.13389480265323, + "p50": 420.3916975093307, + "p90": 557.5033120956505, + "p95": 581.2123146577505, + "p99": 686.7281405249375 + }, + "tpot_ms": { + "mean": 7.672143939324046, + "p50": 7.918229260161499, + "p90": 8.181102878817748, + "p95": 8.271288068884912, + "p99": 8.300791830289597 + }, + "itl_ms": { + "mean": 8.881502143883546, + "p50": 7.747493014903739, + "p90": 8.15649639698677, + "p95": 13.578455609967932, + "p99": 36.924229603027925 + }, + "gpu_memory": { + "peak_used_mb": 134302.0, + "avg_used_mb": 134302.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_4_131072_512.jsonl" + }, + { + "name": "c1_i262144_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 262144, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 21.95894926597248, + "request_throughput": 0.22769759788770882, + "input_token_throughput": 34775.52549307653, + "output_token_throughput": 17.25947791988833, + "total_token_throughput": 34792.784970996414, + "total_input_tokens": 763634, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 4389.704544801498, + "p50": 5417.287694988772, + "p90": 7652.186370198615, + "p95": 8216.366721596569, + "p99": 8667.711002714932 + }, + "ttft_ms": { + "mean": 3949.9581184005365, + "p50": 5366.542825999204, + "p90": 7064.6827823948115, + "p95": 7547.155738197034, + "p99": 7933.134102838812 + }, + "tpot_ms": { + "mean": 5.314242966814787, + "p50": 5.8620529295220765, + "p90": 6.238149659580012, + "p95": 6.248887207276749, + "p99": 6.257477245434139 + }, + "itl_ms": { + "mean": 7.023914325863314, + "p50": 7.034406007733196, + "p90": 7.234651799080893, + "p95": 7.318750605918467, + "p99": 11.975427612196649 + }, + "gpu_memory": { + "peak_used_mb": 134304.0, + "avg_used_mb": 134302.73913043478, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_262144_128.jsonl" + }, + { + "name": "c2_i262144_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 262144, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 17.299146233010106, + "request_throughput": 0.5780632099009645, + "input_token_throughput": 80576.28863441643, + "output_token_throughput": 43.701578668512916, + "total_token_throughput": 80619.99021308494, + "total_input_tokens": 1393901, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 2911.29859109933, + "p50": 1588.1151799985673, + "p90": 7329.382639605319, + "p95": 7493.520934291882, + "p99": 7624.831570041133 + }, + "ttft_ms": { + "mean": 1811.4683610998327, + "p50": 704.2788730032044, + "p90": 5830.754057096783, + "p95": 6405.292088544227, + "p99": 6864.922513702186 + }, + "tpot_ms": { + "mean": 12.037992758067379, + "p50": 6.531740300510898, + "p90": 13.113503143811732, + "p95": 40.837272541715954, + "p99": 63.01628806003945 + }, + "itl_ms": { + "mean": 18.799718608482717, + "p50": 7.143330993130803, + "p90": 12.45063220849261, + "p95": 20.016222586855275, + "p99": 397.8567520412612 + }, + "gpu_memory": { + "peak_used_mb": 134304.0, + "avg_used_mb": 134304.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_2_262144_128.jsonl" + }, + { + "name": "c1_i262144_o256", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 262144, + "output_len": 256, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 5.492067698010942, + "request_throughput": 0.9104039270693707, + "input_token_throughput": 139043.07848873836, + "output_token_throughput": 92.31495820483418, + "total_token_throughput": 139135.3934469432, + "total_input_tokens": 763634, + "total_output_tokens": 507, + "e2e_ms": { + "mean": 1096.547552390257, + "p50": 977.0184349908959, + "p90": 1619.9407393927686, + "p95": 1644.6769221976865, + "p99": 1664.4658684416208 + }, + "ttft_ms": { + "mean": 483.5241790045984, + "p50": 427.5413209979888, + "p90": 664.6515952073969, + "p95": 741.0604366043117, + "p99": 802.1875097218435 + }, + "tpot_ms": { + "mean": 5.448600248984309, + "p50": 6.018701760138747, + "p90": 6.444691271133902, + "p95": 6.504228704678525, + "p99": 6.551858651514223 + }, + "itl_ms": { + "mean": 6.981518899808173, + "p50": 7.025405997410417, + "p90": 7.230082410387695, + "p95": 7.303182306350208, + "p99": 11.031649834476413 + }, + "gpu_memory": { + "peak_used_mb": 134304.0, + "avg_used_mb": 134304.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_262144_256.jsonl" + }, + { + "name": "c2_i262144_o256", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 262144, + "output_len": 256, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 8.155221176013583, + "request_throughput": 1.226208312953221, + "input_token_throughput": 170921.2993633808, + "output_token_throughput": 171.17868048826966, + "total_token_throughput": 171092.47804386905, + "total_input_tokens": 1393901, + "total_output_tokens": 1396, + "e2e_ms": { + "mean": 1528.3535980037414, + "p50": 1439.8152739886427, + "p90": 1988.2277190132297, + "p95": 2101.097439012665, + "p99": 2191.3932150122127 + }, + "ttft_ms": { + "mean": 588.1965045962716, + "p50": 540.3380134957843, + "p90": 763.7523676938143, + "p95": 872.867106342164, + "p99": 960.1588972608442 + }, + "tpot_ms": { + "mean": 6.689213261609457, + "p50": 6.6852245617160255, + "p90": 7.057503772096951, + "p95": 7.161944660791931, + "p99": 7.2454973717479145 + }, + "itl_ms": { + "mean": 8.125442223882589, + "p50": 7.247152010677382, + "p90": 7.577662786934525, + "p95": 11.998600204242393, + "p99": 27.029610665049447 + }, + "gpu_memory": { + "peak_used_mb": 134304.0, + "avg_used_mb": 134304.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_2_262144_256.jsonl" + }, + { + "name": "c1_i524288_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 524288, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 21.47346921497956, + "request_throughput": 0.23284546851479768, + "input_token_throughput": 47769.55180043443, + "output_token_throughput": 17.649686513421663, + "total_token_throughput": 47787.201486947844, + "total_input_tokens": 1025778, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 4292.933715006802, + "p50": 812.884353013942, + "p90": 11330.1644160063, + "p95": 14596.886557008835, + "p99": 17210.26426981087 + }, + "ttft_ms": { + "mean": 3868.1056150060613, + "p50": 447.73642800282687, + "p90": 10681.944887607826, + "p95": 13982.401888811726, + "p99": 16622.76748977485 + }, + "tpot_ms": { + "mean": 5.175154858090192, + "p50": 5.693625568585726, + "p90": 5.999625637622856, + "p95": 6.096606657665045, + "p99": 6.174191473698796 + }, + "itl_ms": { + "mean": 7.127220278598787, + "p50": 7.100967501173727, + "p90": 7.371948787476867, + "p95": 7.5303360528778285, + "p99": 13.657342679798576 + }, + "gpu_memory": { + "peak_used_mb": 134304.0, + "avg_used_mb": 134304.0, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_524288_128.jsonl" + }, + { + "name": "c2_i524288_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 524288, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 5.669274649990257, + "request_throughput": 1.7638940812326294, + "input_token_throughput": 292108.79737548897, + "output_token_throughput": 133.35039254118678, + "total_token_throughput": 292242.1477680301, + "total_input_tokens": 1656045, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 1126.3942198012955, + "p50": 1179.683152004145, + "p90": 1650.5098093184642, + "p95": 1682.9271176538896, + "p99": 1708.8609643222298 + }, + "ttft_ms": { + "mean": 645.4665984987514, + "p50": 532.4026479938766, + "p90": 1085.0829599949066, + "p95": 1167.1218074916394, + "p99": 1232.752885489026 + }, + "tpot_ms": { + "mean": 5.6435321089686115, + "p50": 6.41863733328779, + "p90": 6.854364659400855, + "p95": 6.899553045213209, + "p99": 6.935703753863092 + }, + "itl_ms": { + "mean": 9.410653624309084, + "p50": 7.158250984502956, + "p90": 12.58740501361899, + "p95": 18.499862009775825, + "p99": 67.42094629444139 + }, + "gpu_memory": { + "peak_used_mb": 134306.0, + "avg_used_mb": 134304.06666666668, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": true, + "tpot_mean_ok": true, + "overall": "✅" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_2_524288_128.jsonl" + }, + { + "name": "c1_i1048576_o128", + "config": { + "phase": "main", + "concurrency": 1, + "input_len": 1048576, + "output_len": 128, + "dataset": "random", + "num_prompts": 5 + }, + "metrics": { + "success": 5, + "failed": 0, + "duration_s": 52.218247757002246, + "request_throughput": 0.09575196822512148, + "input_token_throughput": 29684.37407576823, + "output_token_throughput": 7.257999191464208, + "total_token_throughput": 29691.632074959696, + "total_input_tokens": 1550066, + "total_output_tokens": 379, + "e2e_ms": { + "mean": 10442.118058208143, + "p50": 1504.5330520079006, + "p90": 29315.70396400057, + "p95": 38536.12910800147, + "p99": 45912.4692232022 + }, + "ttft_ms": { + "mean": 10048.045438004192, + "p50": 768.1465140194632, + "p90": 28969.904984202007, + "p95": 38265.961359604255, + "p99": 45702.80645992607 + }, + "tpot_ms": { + "mean": 4.670817527462662, + "p50": 5.614634058849119, + "p90": 5.992841449196221, + "p95": 6.039340303062727, + "p99": 6.076539386155933 + }, + "itl_ms": { + "mean": 7.190266562061534, + "p50": 7.141470996430144, + "p90": 7.409438196918927, + "p95": 7.556129548174793, + "p99": 12.29528843308791 + }, + "gpu_memory": { + "peak_used_mb": 134310.0, + "avg_used_mb": 134307.47368421053, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_1_1048576_128.jsonl" + }, + { + "name": "c2_i1048576_o128", + "config": { + "phase": "main", + "concurrency": 2, + "input_len": 1048576, + "output_len": 128, + "dataset": "random", + "num_prompts": 10 + }, + "metrics": { + "success": 10, + "failed": 0, + "duration_s": 122.7578322670015, + "request_throughput": 0.08146119734543486, + "input_token_throughput": 26303.07932594507, + "output_token_throughput": 6.158466519314875, + "total_token_throughput": 26309.237792464384, + "total_input_tokens": 3228909, + "total_output_tokens": 756, + "e2e_ms": { + "mean": 24549.48970649275, + "p50": 4756.214266992174, + "p90": 61223.59725128044, + "p95": 63918.14225814305, + "p99": 66073.77826363314 + }, + "ttft_ms": { + "mean": 23067.16758919356, + "p50": 4525.840376983979, + "p90": 59377.30671290483, + "p95": 59936.56773844705, + "p99": 60383.97655888082 + }, + "tpot_ms": { + "mean": 15.730498989072503, + "p50": 5.885290517918038, + "p90": 41.93317375993312, + "p95": 56.69309552073888, + "p99": 68.50103292938354 + }, + "itl_ms": { + "mean": 26.2815643422692, + "p50": 7.6735740003641695, + "p90": 15.467662602895867, + "p95": 269.72740284109045, + "p99": 347.4504445269122 + }, + "gpu_memory": { + "peak_used_mb": 134312.0, + "avg_used_mb": 134310.22972972973, + "peak_utilization_pct": 100.0, + "memory_total_mb": 143771.0 + } + }, + "slo_status": { + "ttft_p95_ok": false, + "tpot_mean_ok": true, + "overall": "⚠️" + }, + "raw_file": "/data/user1/yy/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/raw_outputs/vllm_main_2_1048576_128.jsonl" + } + ] +} \ No newline at end of file diff --git a/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/scenarios.tsv b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/scenarios.tsv new file mode 100644 index 0000000..3717ac1 --- /dev/null +++ b/experiments/dsv4_h200_vllm_tp_dp_matrix/results/20260709-152419_matrix/tp8_dp1/scenarios.tsv @@ -0,0 +1,57 @@ +mark input_len output_len concurrency num_prompts +Y 1024 128 1 5 +Y 1024 128 128 640 +Y 1024 256 1 5 +Y 1024 256 128 640 +Y 1024 512 1 5 +Y 1024 512 128 640 +Y 1024 1024 1 5 +Y 1024 1024 128 640 +Y 1024 2048 1 5 +Y 1024 2048 128 640 +Y 1024 4096 1 5 +Y 1024 4096 128 640 +Y 4096 128 1 5 +Y 4096 128 64 320 +Y 4096 256 1 5 +Y 4096 256 64 320 +Y 4096 512 1 5 +Y 4096 512 64 320 +Y 4096 1024 1 5 +Y 4096 1024 64 320 +Y 4096 2048 1 5 +Y 4096 2048 64 320 +Y 4096 4096 1 5 +Y 4096 4096 64 320 +Y 16384 128 1 5 +Y 16384 128 32 160 +Y 16384 256 1 5 +Y 16384 256 32 160 +Y 16384 512 1 5 +Y 16384 512 32 160 +Y 16384 1024 1 5 +Y 16384 1024 32 160 +Y 16384 2048 1 5 +Y 16384 2048 32 160 +Y 65536 128 1 5 +Y 65536 128 8 40 +Y 65536 256 1 5 +Y 65536 256 8 40 +Y 65536 512 1 5 +Y 65536 512 8 40 +Y 65536 1024 1 5 +Y 65536 1024 8 40 +Y 131072 128 1 5 +Y 131072 128 4 20 +Y 131072 256 1 5 +Y 131072 256 4 20 +Y 131072 512 1 5 +Y 131072 512 4 20 +Y 262144 128 1 5 +Y 262144 128 2 10 +Y 262144 256 1 5 +Y 262144 256 2 10 +Y 524288 128 1 5 +Y 524288 128 2 10 +Y 1048576 128 1 5 +Y 1048576 128 2 10