From 80959cf7650c116d7d9e9d98945d7a72556aa72f Mon Sep 17 00:00:00 2001 From: yy-fighting Date: Wed, 8 Jul 2026 11:06:49 +0000 Subject: [PATCH] docs: move SLO_STANDARDS.md from scripts/ to docs/; update references --- README.md | 4 +- {scripts => docs}/SLO_STANDARDS.md | 0 .../results/20260708-094838/comparison.md | 2 +- .../results/20260708-092556/comparison.md | 2 +- .../dsv4_h200_long_context_matrix/compare.py | 4 +- .../20260708-100016/sglang/results.json | 42 +++++++++++++++++++ .../results/20260708-100016/vllm/results.json | 42 +++++++++++++++++++ .../results/20260708-083346/comparison.md | 2 +- 8 files changed, 91 insertions(+), 7 deletions(-) rename {scripts => docs}/SLO_STANDARDS.md (100%) create mode 100644 experiments/dsv4_h200_long_context_matrix/results/20260708-100016/sglang/results.json create mode 100644 experiments/dsv4_h200_long_context_matrix/results/20260708-100016/vllm/results.json diff --git a/README.md b/README.md index 203a7e8..80832b5 100644 --- a/README.md +++ b/README.md @@ -13,7 +13,7 @@ | `experiments/` | 以实验为单位的自包含目录（脚本 + 配置 + 结果） | | `experiments/legacy_bench_results/` | 历史归档的实验产物（只读），从原 `bench_results/` 迁移而来 | | `BENCHMARK_WORKFLOW.md` | benchmark 目录与命名规范 | -| `scripts/SLO_STANDARDS.md` | 推理服务 SLO 标准（TTFT/TPOT） | +| `docs/SLO_STANDARDS.md` | 推理服务 SLO 标准（TTFT/TPOT） | > 注：`.gitignore` 已排除 `envs/`、`deps/`、`tmp/`、`datasets/`、`logs/`、`*.zip`、原始 `raw_outputs/*.jsonl` 等大文件/中间文件。 @@ -99,7 +99,7 @@ python3 experiments/dsv4_h200_dspark/parse_results.py \ ## SLO 参考 -详见 `scripts/SLO_STANDARDS.md`。 +详见 `docs/SLO_STANDARDS.md`。 主要关注指标： diff --git a/scripts/SLO_STANDARDS.md b/docs/SLO_STANDARDS.md similarity index 100% rename from scripts/SLO_STANDARDS.md rename to docs/SLO_STANDARDS.md diff --git a/experiments/dsv4_h200_256k_4k_probe/results/20260708-094838/comparison.md b/experiments/dsv4_h200_256k_4k_probe/results/20260708-094838/comparison.md index f31e46b..f668e9a 100644 --- a/experiments/dsv4_h200_256k_4k_probe/results/20260708-094838/comparison.md +++ b/experiments/dsv4_h200_256k_4k_probe/results/20260708-094838/comparison.md @@ -17,5 +17,5 @@ ## Notes -- SLO check uses TTFT P95 and TPOT mean (the same criteria as `scripts/SLO_STANDARDS.md`). +- SLO check uses TTFT P95 and TPOT mean (the same criteria as `docs/SLO_STANDARDS.md`). - A ⚠️ indicates one of the two metrics is out of target; ❌ indicates both are out. diff --git a/experiments/dsv4_h200_64k_sglang_vs_vllm/results/20260708-092556/comparison.md b/experiments/dsv4_h200_64k_sglang_vs_vllm/results/20260708-092556/comparison.md index e73a8ce..00bdd81 100644 --- a/experiments/dsv4_h200_64k_sglang_vs_vllm/results/20260708-092556/comparison.md +++ b/experiments/dsv4_h200_64k_sglang_vs_vllm/results/20260708-092556/comparison.md @@ -19,5 +19,5 @@ ## Notes -- SLO check uses TTFT P95 and TPOT mean (the same criteria as `scripts/SLO_STANDARDS.md`). +- SLO check uses TTFT P95 and TPOT mean (the same criteria as `docs/SLO_STANDARDS.md`). - A ⚠️ indicates one of the two metrics is out of target; ❌ indicates both are out. diff --git a/experiments/dsv4_h200_long_context_matrix/compare.py b/experiments/dsv4_h200_long_context_matrix/compare.py index 0f4eb51..1b9b432 100755 --- a/experiments/dsv4_h200_long_context_matrix/compare.py +++ b/experiments/dsv4_h200_long_context_matrix/compare.py @@ -18,7 +18,7 @@ def load_result(result_root: Path) -> dict: def slo_status(ttft_p95_ms: float, tpot_mean_ms: float) -> str: - # S2 tier targets from scripts/SLO_STANDARDS.md. + # S2 tier targets from docs/SLO_STANDARDS.md. ttft_ok = ttft_p95_ms < 3000.0 tpot_ok = tpot_mean_ms < 50.0 if ttft_ok and tpot_ok: @@ -75,7 +75,7 @@ def main(): ) f.write("\n## Notes\n\n") - f.write("- SLO check uses TTFT P95 and TPOT mean (the same criteria as `scripts/SLO_STANDARDS.md`).\n") + f.write("- SLO check uses TTFT P95 and TPOT mean (the same criteria as `docs/SLO_STANDARDS.md`).\n") f.write("- A ⚠️ indicates one of the two metrics is out of target; ❌ indicates both are out.\n") print(f"Wrote comparison to {args.output}") diff --git a/experiments/dsv4_h200_long_context_matrix/results/20260708-100016/sglang/results.json b/experiments/dsv4_h200_long_context_matrix/results/20260708-100016/sglang/results.json new file mode 100644 index 0000000..926f365 --- /dev/null +++ b/experiments/dsv4_h200_long_context_matrix/results/20260708-100016/sglang/results.json @@ -0,0 +1,42 @@ +{ + "metadata": { + "experiment": "dsv4_h200_long_context_matrix_sglang", + "run_id": "20260708-100016", + "timestamp": "2026-07-08T10:00:20+00:00", + "model": "/data/models/DeepSeek-V4-Flash", + "backend": "sglang", + "engine": "sglang", + "hardware": "8x NVIDIA H200 143GB", + "accelerator": "NVIDIA H200", + "chip": "nvidia_h200", + "script": "experiments/dsv4_h200_long_context_matrix/run_bench.sh", + "env": "/data/user1/yy/envs/sglang", + "git_commit": "7e35945", + "git_dirty": "dirty", + "description": "H200 long-context matrix sglang TP=8 for DeepSeek-V4-Flash" + }, + "config": { + "tp": 8, + "cuda_visible_devices": "0,1,2,3,4,5,6,7", + "backend": "sglang", + "server_start_script": "experiments/dsv4_h200_long_context_matrix/start_sglang.sh", + "groups": [ + { + "label": "64k", + "max_model_len": 80000, + "max_slots": 25 + }, + { + "label": "128k", + "max_model_len": 140000, + "max_slots": 10 + }, + { + "label": "256k", + "max_model_len": 270000, + "max_slots": 10 + } + ] + }, + "scenarios": [] +} diff --git a/experiments/dsv4_h200_long_context_matrix/results/20260708-100016/vllm/results.json b/experiments/dsv4_h200_long_context_matrix/results/20260708-100016/vllm/results.json new file mode 100644 index 0000000..7a2af01 --- /dev/null +++ b/experiments/dsv4_h200_long_context_matrix/results/20260708-100016/vllm/results.json @@ -0,0 +1,42 @@ +{ + "metadata": { + "experiment": "dsv4_h200_long_context_matrix_vllm", + "run_id": "20260708-100016", + "timestamp": "2026-07-08T10:00:20+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_long_context_matrix/run_bench.sh", + "env": "/data/user1/yy/envs/vllm", + "git_commit": "7e35945", + "git_dirty": "dirty", + "description": "H200 long-context matrix vllm TP=8 for DeepSeek-V4-Flash" + }, + "config": { + "tp": 8, + "cuda_visible_devices": "0,1,2,3,4,5,6,7", + "backend": "vllm", + "server_start_script": "experiments/dsv4_h200_long_context_matrix/start_vllm.sh", + "groups": [ + { + "label": "64k", + "max_model_len": 80000, + "max_slots": 25 + }, + { + "label": "128k", + "max_model_len": 140000, + "max_slots": 10 + }, + { + "label": "256k", + "max_model_len": 270000, + "max_slots": 10 + } + ] + }, + "scenarios": [] +} diff --git a/experiments/dsv4_h200_sglang_vs_vllm/results/20260708-083346/comparison.md b/experiments/dsv4_h200_sglang_vs_vllm/results/20260708-083346/comparison.md index dfc98f0..8176b41 100644 --- a/experiments/dsv4_h200_sglang_vs_vllm/results/20260708-083346/comparison.md +++ b/experiments/dsv4_h200_sglang_vs_vllm/results/20260708-083346/comparison.md @@ -37,5 +37,5 @@ ## Notes -- SLO check uses TTFT P95 and TPOT mean (the same criteria as `scripts/SLO_STANDARDS.md`). +- SLO check uses TTFT P95 and TPOT mean (the same criteria as `docs/SLO_STANDARDS.md`). - A ⚠️ indicates one of the two metrics is out of target; ❌ indicates both are out.