dsr1-fp4-1k1k-mid-curve

concurrency 512 · 20 days ago

cron

passed

re-run

Commit

SHA3b7a258

[CPU] upgrade dependent torch ver to PT2.12 (#21456)

ZailiWang·20 days ago

PR #21456 · [CPU] upgrade dependent torch ver to PT2.12

Run

GitHub Actions26928315759-1

Slurm job5116

GPUs48·prefill 16 / decode 32

ISL / OSL1024 / 1024

Logscron/26928315759-1/1k1k/dsr1-fp4-1k1k-mid-curve/2026-06-04/5116/sa-bench_isl_1024_osl_1024/

Metrics

28 captured

best_of

1.00

burstiness

1.00

completed

5,120

duration

154

max_concurrency

512

mean_e2el_ms

14,790ms

mean_itl_ms

734ms

mean_tpot_ms

14.98ms

mean_ttft_ms

984ms

median_e2el_ms

14,751ms

median_itl_ms

722ms

median_tpot_ms

15.16ms

median_ttft_ms

729ms

num_prompts

5,120

output_throughput

30,665tok/s

p99_e2el_ms

17,901ms

p99_itl_ms

1,115ms

p99_tpot_ms

15.86ms

p99_ttft_ms

3,940ms

peak_output_tokens_per_s

37,962s

request_throughput

33.25tok/s

std_e2el_ms

1,184ms

std_itl_ms

160ms

std_tpot_ms

0.78ms

std_ttft_ms

940ms

total_input_tokens

4,717,859

total_output_tokens

4,722,209

total_token_throughput

61,302tok/s