qqtang/sskj
1
3
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
sskj/docs/dsv4pro_pro6000d_2node_sglang/results/dsv4pro-phase1-full-20260730-220916/summary.jsonl

13 lines
20 KiB
JSON
Raw Blame History

{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "balanced_32k_to_1k_c8", "role": "", "stage": "balanced", "repetition": 1, "isl": 32768, "osl": 1024, "concurrency": 8, "num_prompts": 8, "warmup_requests": 0, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:28:41+0800", "ended_at": "2026-07-30T22:31:22+0800", "elapsed_s": 161.0, "completed": 8, "failed": 0, "duration_s": 128.62811431800947, "actual_concurrency": 7.996993535425267, "peak_concurrent_requests": null, "total_input_tokens": 262144, "total_output_tokens": 8192, "request_throughput": 0.06219480120979978, "input_token_throughput": 2037.9992460427193, "output_token_throughput": 63.68747643883498, "total_token_throughput": 2101.686722481554, "peak_output_token_throughput": null, "e2e_mean_ms": 128579.77483438299, "e2e_p50_ms": 128578.26417451724, "e2e_p95_ms": 128588.8987001963, "e2e_p99_ms": 128589.40238882786, "ttft_mean_ms": 49665.467494261975, "ttft_p50_ms": 49563.69844998699, "ttft_p95_ms": 82083.64989476977, "ttft_p99_ms": 83746.94262376754, "tpot_mean_ms": 77.14008537646238, "tpot_p50_ms": 77.23808966229743, "tpot_p95_ms": 109.32309288714016, "tpot_p99_ms": 112.17132956471158, "itl_mean_ms": 77.14005810044779, "itl_p50_ms": 43.40646349010058, "itl_p95_ms": 43.84165157971437, "itl_p99_ms": 45.188912986195646, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/balanced_32k_to_1k_c8/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/balanced_32k_to_1k_c8/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "mixed", "case_id": "decode_control_1k_to_1k_c32", "role": "control", "stage": "mixed_interference", "repetition": 1, "isl": 1024, "osl": 1024, "concurrency": 32, "num_prompts": 64, "warmup_requests": 1, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:31:28+0800", "ended_at": "2026-07-30T22:34:26+0800", "elapsed_s": 178.0, "completed": 64, "failed": 0, "duration_s": 143.81865712802391, "actual_concurrency": 31.98259215252821, "peak_concurrent_requests": null, "total_input_tokens": 65536, "total_output_tokens": 65536, "request_throughput": 0.44500485040010307, "input_token_throughput": 455.68496680970554, "output_token_throughput": 455.68496680970554, "total_token_throughput": 911.3699336194111, "peak_output_token_throughput": null, "e2e_mean_ms": 71870.21023202942, "e2e_p50_ms": 71867.41446750239, "e2e_p95_ms": 72007.63789927005, "e2e_p99_ms": 72012.73389439622, "ttft_mean_ms": 7370.452653370194, "ttft_p50_ms": 6938.839260517852, "ttft_p95_ms": 9442.636363586644, "ttft_p99_ms": 9443.245556704933, "tpot_mean_ms": 63.04961640142642, "tpot_p50_ms": 63.471088219448355, "tpot_p95_ms": 65.88327712923635, "tpot_p99_ms": 67.80910156527888, "itl_mean_ms": 63.049588087913975, "itl_p50_ms": 60.98580302204937, "itl_p95_ms": 61.753195300116204, "itl_p99_ms": 63.56921844591854, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_control_1k_to_1k_c32/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_control_1k_to_1k_c32/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "decode_latency_1k_to_1k_c1", "role": "", "stage": "decode_latency", "repetition": 1, "isl": 1024, "osl": 1024, "concurrency": 1, "num_prompts": 1, "warmup_requests": 1, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:21:44+0800", "ended_at": "2026-07-30T22:22:50+0800", "elapsed_s": 66.0, "completed": 1, "failed": 0, "duration_s": 32.59594450396253, "actual_concurrency": 0.9987527008467322, "peak_concurrent_requests": null, "total_input_tokens": 1024, "total_output_tokens": 1024, "request_throughput": 0.03067866310419184, "input_token_throughput": 31.414951018692445, "output_token_throughput": 31.414951018692445, "total_token_throughput": 62.82990203738489, "peak_output_token_throughput": null, "e2e_mean_ms": 32555.28760998277, "e2e_p50_ms": 32555.28760998277, "e2e_p95_ms": 32555.28760998277, "e2e_p99_ms": 32555.28760998277, "ttft_mean_ms": 363.2723209448159, "ttft_p50_ms": 363.2723209448159, "ttft_p95_ms": 363.2723209448159, "ttft_p99_ms": 363.2723209448159, "tpot_mean_ms": 31.468245639333286, "tpot_p50_ms": 31.468245639333286, "tpot_p95_ms": 31.468245639333286, "tpot_p99_ms": 31.468245639333286, "itl_mean_ms": 31.468210095789587, "itl_p50_ms": 31.49253799347207, "itl_p95_ms": 31.659404194215313, "itl_p99_ms": 32.3411487112753, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_latency_1k_to_1k_c1/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_latency_1k_to_1k_c1/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "decode_throughput_1k_to_1k_c16", "role": "", "stage": "decode_throughput", "repetition": 1, "isl": 1024, "osl": 1024, "concurrency": 16, "num_prompts": 16, "warmup_requests": 1, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:22:56+0800", "ended_at": "2026-07-30T22:24:25+0800", "elapsed_s": 89.0, "completed": 16, "failed": 0, "duration_s": 55.48426674498478, "actual_concurrency": 15.986115557256861, "peak_concurrent_requests": null, "total_input_tokens": 16384, "total_output_tokens": 16384, "request_throughput": 0.28837003602370287, "input_token_throughput": 295.29091688827174, "output_token_throughput": 295.29091688827174, "total_token_throughput": 590.5818337765435, "peak_output_token_throughput": null, "e2e_mean_ms": 55436.11873718692, "e2e_p50_ms": 55437.53465998452, "e2e_p95_ms": 55443.82167501317, "e2e_p99_ms": 55447.12010782387, "ttft_mean_ms": 4706.02819519263, "ttft_p50_ms": 4801.126986538293, "ttft_p95_ms": 4950.267374995747, "ttft_p99_ms": 4950.924708603998, "tpot_mean_ms": 49.58953132159755, "tpot_p50_ms": 49.49641186020903, "tpot_p95_ms": 50.01878498413362, "tpot_p99_ms": 50.915034893211796, "itl_mean_ms": 49.58950283761395, "itl_p50_ms": 49.32670452399179, "itl_p95_ms": 49.8873026604997, "itl_p99_ms": 52.25673661392648, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_throughput_1k_to_1k_c16/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_throughput_1k_to_1k_c16/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "decode_throughput_1k_to_1k_c32", "role": "", "stage": "decode_throughput", "repetition": 1, "isl": 1024, "osl": 1024, "concurrency": 32, "num_prompts": 32, "warmup_requests": 1, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:24:30+0800", "ended_at": "2026-07-30T22:26:15+0800", "elapsed_s": 105.0, "completed": 32, "failed": 0, "duration_s": 70.97485623596003, "actual_concurrency": 31.975931620502816, "peak_concurrent_requests": null, "total_input_tokens": 32768, "total_output_tokens": 32768, "request_throughput": 0.4508638931738606, "input_token_throughput": 461.68462661003326, "output_token_throughput": 461.68462661003326, "total_token_throughput": 923.3692532200665, "peak_output_token_throughput": null, "e2e_mean_ms": 70921.47343050237, "e2e_p50_ms": 70921.31606096518, "e2e_p95_ms": 70933.18627287517, "e2e_p99_ms": 70935.98751158977, "ttft_mean_ms": 6650.527383468216, "ttft_p50_ms": 6178.440199000761, "ttft_p95_ms": 8021.852347906679, "ttft_p99_ms": 8023.242657405207, "tpot_mean_ms": 62.825949215087164, "tpot_p50_ms": 63.29258629570958, "tpot_p95_ms": 63.30661669023356, "tpot_p99_ms": 65.29997366317116, "itl_mean_ms": 62.82592070965087, "itl_p50_ms": 61.42424049903639, "itl_p95_ms": 62.237933481810614, "itl_p99_ms": 64.6031521842815, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_throughput_1k_to_1k_c32/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_throughput_1k_to_1k_c32/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "decode_throughput_1k_to_1k_c64", "role": "", "stage": "decode_throughput", "repetition": 1, "isl": 1024, "osl": 1024, "concurrency": 64, "num_prompts": 64, "warmup_requests": 1, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:26:20+0800", "ended_at": "2026-07-30T22:28:36+0800", "elapsed_s": 136.0, "completed": 64, "failed": 0, "duration_s": 101.22691119497176, "actual_concurrency": 63.94603747793439, "peak_concurrent_requests": null, "total_input_tokens": 65536, "total_output_tokens": 65536, "request_throughput": 0.6322429405825737, "input_token_throughput": 647.4167711565555, "output_token_throughput": 647.4167711565555, "total_token_throughput": 1294.833542313111, "peak_output_token_throughput": null, "e2e_mean_ms": 101141.56026639376, "e2e_p50_ms": 101148.19569600513, "e2e_p95_ms": 101163.1970004586, "e2e_p99_ms": 101167.44335912867, "ttft_mean_ms": 7978.397482784203, "ttft_p50_ms": 6505.179281026358, "ttft_p95_ms": 12716.491229846724, "ttft_p99_ms": 12719.49685954547, "tpot_mean_ms": 91.06858532122146, "tpot_p50_ms": 92.52174521165054, "tpot_p95_ms": 93.44459645826957, "tpot_p99_ms": 94.39186767905878, "itl_mean_ms": 91.06855870121748, "itl_p50_ms": 86.24391999910586, "itl_p95_ms": 87.80462378927041, "itl_p99_ms": 90.7129056059057, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_throughput_1k_to_1k_c64/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_throughput_1k_to_1k_c64/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "mixed", "case_id": "decode_with_128k_prefill_1k_to_1k_c32", "role": "decode_background", "stage": "mixed_interference", "repetition": 1, "isl": 1024, "osl": 1024, "concurrency": 32, "num_prompts": 64, "warmup_requests": 0, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:34:26+0800", "ended_at": "2026-07-30T22:38:09+0800", "elapsed_s": 223.0, "completed": 64, "failed": 0, "duration_s": 189.43961485201726, "actual_concurrency": 31.98654958092739, "peak_concurrent_requests": null, "total_input_tokens": 65536, "total_output_tokens": 65536, "request_throughput": 0.3378385246929174, "input_token_throughput": 345.94664928554744, "output_token_throughput": 345.94664928554744, "total_token_throughput": 691.8932985710949, "peak_output_token_throughput": null, "e2e_mean_ms": 94679.9942664975, "e2e_p50_ms": 94677.34680901049, "e2e_p95_ms": 117629.63820034638, "e2e_p99_ms": 117636.8834006862, "ttft_mean_ms": 7749.917391879535, "ttft_p50_ms": 7705.110649490962, "ttft_p95_ms": 10193.896457596566, "ttft_p99_ms": 10196.455221220385, "tpot_mean_ms": 84.97563721859039, "tpot_p50_ms": 86.47172644327328, "tpot_p95_ms": 109.7299457727384, "tpot_p99_ms": 110.56891953740994, "itl_mean_ms": 84.97560842059728, "itl_p50_ms": 60.77706499490887, "itl_p95_ms": 61.61956858995836, "itl_p99_ms": 64.70431641500909, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_with_128k_prefill_1k_to_1k_c32/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/decode_with_128k_prefill_1k_to_1k_c32/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "mixed", "case_id": "long_prefill_injection_128k_to_1_c1", "role": "prefill_injection", "stage": "mixed_interference", "repetition": 1, "isl": 131072, "osl": 1, "concurrency": 1, "num_prompts": 1, "warmup_requests": 0, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:35:06+0800", "ended_at": "2026-07-30T22:36:24+0800", "elapsed_s": 78.0, "completed": 1, "failed": 0, "duration_s": 45.83367280900711, "actual_concurrency": 0.9982227218104723, "peak_concurrent_requests": null, "total_input_tokens": 131072, "total_output_tokens": 1, "request_throughput": 0.021818020217735695, "input_token_throughput": 2859.731545979053, "output_token_throughput": 0.021818020217735695, "total_token_throughput": 2859.7533639992707, "peak_output_token_throughput": null, "e2e_mean_ms": 45752.21362197772, "e2e_p50_ms": 45752.21362197772, "e2e_p95_ms": 45752.21362197772, "e2e_p99_ms": 45752.21362197772, "ttft_mean_ms": 45752.13837000774, "ttft_p50_ms": 45752.13837000774, "ttft_p95_ms": 45752.13837000774, "ttft_p99_ms": 45752.13837000774, "tpot_mean_ms": 0.0, "tpot_p50_ms": 0.0, "tpot_p95_ms": 0.0, "tpot_p99_ms": 0.0, "itl_mean_ms": 0.0, "itl_p50_ms": 0.0, "itl_p95_ms": 0.0, "itl_p99_ms": 0.0, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/long_prefill_injection_128k_to_1_c1/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/long_prefill_injection_128k_to_1_c1/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "long_prefill_latency_128k_c1", "role": "", "stage": "prefill_latency", "repetition": 1, "isl": 131072, "osl": 1, "concurrency": 1, "num_prompts": 1, "warmup_requests": 0, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:16:51+0800", "ended_at": "2026-07-30T22:18:12+0800", "elapsed_s": 81.0, "completed": 1, "failed": 0, "duration_s": 48.363155752944294, "actual_concurrency": 0.9996148667368967, "peak_concurrent_requests": null, "total_input_tokens": 131072, "total_output_tokens": 1, "request_throughput": 0.020676897204730506, "input_token_throughput": 2710.162270418437, "output_token_throughput": 0.020676897204730506, "total_token_throughput": 2710.1829473156417, "peak_output_token_throughput": null, "e2e_mean_ms": 48344.52949295519, "e2e_p50_ms": 48344.52949295519, "e2e_p95_ms": 48344.52949295519, "e2e_p99_ms": 48344.52949295519, "ttft_mean_ms": 48344.461318978574, "ttft_p50_ms": 48344.461318978574, "ttft_p95_ms": 48344.461318978574, "ttft_p99_ms": 48344.461318978574, "tpot_mean_ms": 0.0, "tpot_p50_ms": 0.0, "tpot_p95_ms": 0.0, "tpot_p99_ms": 0.0, "itl_mean_ms": 0.0, "itl_p50_ms": 0.0, "itl_p95_ms": 0.0, "itl_p99_ms": 0.0, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/long_prefill_latency_128k_c1/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/long_prefill_latency_128k_c1/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "mid_prefill_latency_32k_c1", "role": "", "stage": "prefill_latency", "repetition": 1, "isl": 32768, "osl": 1, "concurrency": 1, "num_prompts": 1, "warmup_requests": 0, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:16:00+0800", "ended_at": "2026-07-30T22:16:46+0800", "elapsed_s": 46.0, "completed": 1, "failed": 0, "duration_s": 12.352426828991156, "actual_concurrency": 0.9985701137731423, "peak_concurrent_requests": null, "total_input_tokens": 32768, "total_output_tokens": 1, "request_throughput": 0.08095575175988892, "input_token_throughput": 2652.75807366804, "output_token_throughput": 0.08095575175988892, "total_token_throughput": 2652.8390294198, "peak_output_token_throughput": null, "e2e_mean_ms": 12334.764264000114, "e2e_p50_ms": 12334.764264000114, "e2e_p95_ms": 12334.764264000114, "e2e_p99_ms": 12334.764264000114, "ttft_mean_ms": 12334.68782599084, "ttft_p50_ms": 12334.68782599084, "ttft_p95_ms": 12334.68782599084, "ttft_p99_ms": 12334.68782599084, "tpot_mean_ms": 0.0, "tpot_p50_ms": 0.0, "tpot_p95_ms": 0.0, "tpot_p99_ms": 0.0, "itl_mean_ms": 0.0, "itl_p50_ms": 0.0, "itl_p95_ms": 0.0, "itl_p99_ms": 0.0, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/mid_prefill_latency_32k_c1/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/mid_prefill_latency_32k_c1/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "mid_prefill_throughput_32k_c16", "role": "", "stage": "prefill_throughput", "repetition": 1, "isl": 32768, "osl": 1, "concurrency": 16, "num_prompts": 16, "warmup_requests": 0, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:18:18+0800", "ended_at": "2026-07-30T22:21:39+0800", "elapsed_s": 201.0, "completed": 16, "failed": 0, "duration_s": 168.4313552599633, "actual_concurrency": 8.771898294558559, "peak_concurrent_requests": null, "total_input_tokens": 524288, "total_output_tokens": 16, "request_throughput": 0.09499418902914482, "input_token_throughput": 3112.7695861070174, "output_token_throughput": 0.09499418902914482, "total_token_throughput": 3112.8645802960464, "peak_output_token_throughput": null, "e2e_mean_ms": 92341.41987219118, "e2e_p50_ms": 92749.04042950948, "e2e_p95_ms": 162087.50443853205, "e2e_p99_ms": 167117.798359727, "ttft_mean_ms": 92341.37187193119, "ttft_p50_ms": 92748.99350100895, "ttft_p95_ms": 162087.46085499297, "ttft_p99_ms": 167117.75140058598, "tpot_mean_ms": 0.0, "tpot_p50_ms": 0.0, "tpot_p95_ms": 0.0, "tpot_p99_ms": 0.0, "itl_mean_ms": 0.0, "itl_p50_ms": 0.0, "itl_p95_ms": 0.0, "itl_p99_ms": 0.0, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/mid_prefill_throughput_32k_c16/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/mid_prefill_throughput_32k_c16/rep1/bench.log"}
{"run_id": "dsv4pro-phase1-full-20260730-220916", "suite": "fixed", "case_id": "short_prefill_latency_1k_c1", "role": "", "stage": "prefill_latency", "repetition": 1, "isl": 1024, "osl": 1, "concurrency": 1, "num_prompts": 1, "warmup_requests": 1, "status": "COMPLETED", "error_type": "", "exit_code": 0, "started_at": "2026-07-30T22:15:21+0800", "ended_at": "2026-07-30T22:15:55+0800", "elapsed_s": 34.0, "completed": 1, "failed": 0, "duration_s": 0.5198853989713825, "actual_concurrency": 0.9654920680740482, "peak_concurrent_requests": null, "total_input_tokens": 1024, "total_output_tokens": 1, "request_throughput": 1.9235008368739468, "input_token_throughput": 1969.6648569589215, "output_token_throughput": 1.9235008368739468, "total_token_throughput": 1971.5883577957954, "peak_output_token_throughput": null, "e2e_mean_ms": 501.94522901438177, "e2e_p50_ms": 501.94522901438177, "e2e_p95_ms": 501.94522901438177, "e2e_p99_ms": 501.94522901438177, "ttft_mean_ms": 501.89953204244375, "ttft_p50_ms": 501.89953204244375, "ttft_p95_ms": 501.89953204244375, "ttft_p99_ms": 501.89953204244375, "tpot_mean_ms": 0.0, "tpot_p50_ms": 0.0, "tpot_p95_ms": 0.0, "tpot_p99_ms": 0.0, "itl_mean_ms": 0.0, "itl_p50_ms": 0.0, "itl_p95_ms": 0.0, "itl_p99_ms": 0.0, "bench_file": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/short_prefill_latency_1k_c1/rep1/bench.jsonl", "bench_log": "/data/hzy/sskj/experiments/pro6000/dsv4pro_pro6000d_2node_sglang_tp16_quick_map/results/dsv4pro-phase1-full-20260730-220916/cases/short_prefill_latency_1k_c1/rep1/bench.log"}
Reference in New Issue View Git Blame Copy Permalink