dsr1-fp4-1k1k-mid-curve

concurrency 4,096 · 18 days ago

cron

passed

re-run

Commit

SHAbf66b7b

[diffusion] model: support Ideogram4 NVFP4 (#27379)

mickqian·18 days ago

PR #27379 · [diffusion] model: support Ideogram4 NVFP4

Run

GitHub Actions27051102318-1

Slurm job5123

GPUs48·prefill 16 / decode 32

ISL / OSL1024 / 1024

Logscron/27051102318-1/1k1k/dsr1-fp4-1k1k-mid-curve/2026-06-06/5123/sa-bench_isl_1024_osl_1024/

Metrics

28 captured

best_of

1.00

burstiness

1.00

completed

40,960

duration

305

max_concurrency

4,096

mean_e2el_ms

29,750ms

mean_itl_ms

1,103ms

mean_tpot_ms

22.52ms

mean_ttft_ms

9,027ms

median_e2el_ms

29,622ms

median_itl_ms

1,087ms

median_tpot_ms

22.48ms

median_ttft_ms

9,597ms

num_prompts

40,960

output_throughput

123,594tok/s

p99_e2el_ms

45,922ms

p99_itl_ms

2,195ms

p99_tpot_ms

27.61ms

p99_ttft_ms

22,384ms

peak_output_tokens_per_s

162,978s

request_throughput

134tok/s

std_e2el_ms

3,964ms

std_itl_ms

325ms

std_tpot_ms

3.03ms

std_ttft_ms

3,899ms

total_input_tokens

37,769,666

total_output_tokens

37,742,239

total_token_throughput

247,277tok/s