dsr1-fp4-1k1k-mid-curve

best_of

1.00

burstiness

1.00

completed

20,480

duration

201

max_concurrency

2,048

mean_e2el_ms

19,368ms

mean_itl_ms

941ms

mean_tpot_ms

19.21ms

mean_ttft_ms

1,668ms

median_e2el_ms

18,988ms

median_itl_ms

969ms

median_tpot_ms

19.56ms

median_ttft_ms

788ms

num_prompts

20,480

output_throughput

94,167tok/s

p99_e2el_ms

30,121ms

p99_itl_ms

1,531ms

p99_tpot_ms

20.82ms

p99_ttft_ms

12,070ms

peak_output_tokens_per_s

110,385s

request_throughput

102tok/s

std_e2el_ms

2,759ms

std_itl_ms

193ms

std_tpot_ms

1.26ms

std_ttft_ms

2,585ms

total_input_tokens

18,880,692

total_output_tokens

18,888,974

total_token_throughput

188,293tok/s