dsr1-fp4-1k1k-mid-curve

best_of

1.00

burstiness

1.00

completed

5,120

duration

164

max_concurrency

512

mean_e2el_ms

15,757ms

mean_itl_ms

785ms

mean_tpot_ms

16.00ms

mean_ttft_ms

1,006ms

median_e2el_ms

15,721ms

median_itl_ms

781ms

median_tpot_ms

16.16ms

median_ttft_ms

754ms

num_prompts

5,120

output_throughput

28,808tok/s

p99_e2el_ms

19,185ms

p99_itl_ms

1,188ms

p99_tpot_ms

16.81ms

p99_ttft_ms

3,498ms

peak_output_tokens_per_s

35,562s

request_throughput

31.23tok/s

std_e2el_ms

1,239ms

std_itl_ms

164ms

std_tpot_ms

0.78ms

std_ttft_ms

918ms

total_input_tokens

4,717,859

total_output_tokens

4,722,209

total_token_throughput

57,589tok/s