sglang/ GB200 perf

dsr1-fp8-1k1k-max-tpt

concurrency 6,144 · 6 days ago

cron
passed
re-run
Commit

fix (#28597)

liusy58·6 days ago
PR #28597 · fix
Run
GitHub Actions27734450270-1
Slurm job5320
GPUs48·prefill 16 / decode 32
ISL / OSL1024 / 1024

Metrics

28 captured

best_of

1.00

burstiness

1.00

completed

61,440

duration

465

max_concurrency

6,144

mean_e2el_ms

45,116ms

mean_itl_ms

1,796ms

mean_tpot_ms

36.78ms

mean_ttft_ms

11,255ms

median_e2el_ms

44,701ms

median_itl_ms

1,752ms

median_tpot_ms

37.31ms

median_ttft_ms

11,834ms

num_prompts

61,440

output_throughput

121,798tok/s

p99_e2el_ms

70,878ms

p99_itl_ms

3,452ms

p99_tpot_ms

42.93ms

p99_ttft_ms

32,816ms

peak_output_tokens_per_s

172,683s

request_throughput

132tok/s

std_e2el_ms

6,674ms

std_itl_ms

563ms

std_tpot_ms

5.02ms

std_ttft_ms

6,183ms

total_input_tokens

56,636,934

total_output_tokens

56,621,450

total_token_throughput

243,629tok/s