sglang/ GB200 perf

dsr1-fp4-1k1k-mid-curve

concurrency 8,192 · 12 days ago

cron
passed
re-run
Commit

add lfm2.5 to new cookbook. (#27409)

vincentzed·12 days ago
PR #27409 · add lfm2.5 to new cookbook.
Run
GitHub Actions27392321842-1
Slurm job5299
GPUs48·prefill 16 / decode 32
ISL / OSL1024 / 1024

Metrics

28 captured

best_of

1.00

burstiness

1.00

completed

81,920

duration

668

max_concurrency

8,192

mean_e2el_ms

64,619ms

mean_itl_ms

1,187ms

mean_tpot_ms

24.22ms

mean_ttft_ms

42,320ms

median_e2el_ms

66,721ms

median_itl_ms

1,061ms

median_tpot_ms

22.39ms

median_ttft_ms

46,362ms

num_prompts

81,920

output_throughput

112,981tok/s

p99_e2el_ms

81,708ms

p99_itl_ms

3,216ms

p99_tpot_ms

41.01ms

p99_ttft_ms

55,087ms

peak_output_tokens_per_s

161,301s

request_throughput

123tok/s

std_e2el_ms

8,195ms

std_itl_ms

618ms

std_tpot_ms

6.68ms

std_ttft_ms

10,499ms

total_input_tokens

75,511,905

total_output_tokens

75,496,082

total_token_throughput

225,986tok/s