131 lines
4.3 KiB
JSON
131 lines
4.3 KiB
JSON
{
|
|
"model": "/data/models/Qwen3-4B",
|
|
"draft_model": "deepseek-ai/dspark_qwen3_4b_block7",
|
|
"url": "http://127.0.0.1:30003/v1/completions",
|
|
"max_tokens": 256,
|
|
"num_prompts": 500,
|
|
"dataset": "/data/user1/yy/datasets/ShareGPT_filtered_chat.json",
|
|
"timestamp": "20260705_121256",
|
|
"results": [
|
|
{
|
|
"concurrency": 1,
|
|
"num_prompts": 500,
|
|
"duration_s": 181.22913801996037,
|
|
"success_count": 500,
|
|
"fail_count": 0,
|
|
"input_tokens": 108545,
|
|
"output_tokens": 36681,
|
|
"total_tokens": 145226,
|
|
"request_throughput": 2.7589382450460618,
|
|
"input_throughput": 598.9379036170495,
|
|
"output_throughput": 202.4012275330692,
|
|
"total_throughput": 801.3391311501188,
|
|
"mean_ttft_ms": 17.586736707482487,
|
|
"p50_ttft_ms": 15.236841514706612,
|
|
"p99_ttft_ms": 43.418583339080215,
|
|
"mean_tpot_ms": 4.756160026498775,
|
|
"p50_tpot_ms": 4.747943201144331,
|
|
"p99_tpot_ms": 4.845208972490266,
|
|
"mean_e2e_ms": 361.93272305326536,
|
|
"p50_e2e_ms": 369.4158981088549,
|
|
"p99_e2e_ms": 552.2739849891514,
|
|
"errors": []
|
|
},
|
|
{
|
|
"concurrency": 4,
|
|
"num_prompts": 500,
|
|
"duration_s": 49.20666282507591,
|
|
"success_count": 500,
|
|
"fail_count": 0,
|
|
"input_tokens": 108545,
|
|
"output_tokens": 36991,
|
|
"total_tokens": 145536,
|
|
"request_throughput": 10.161225559584139,
|
|
"input_throughput": 2205.900456730121,
|
|
"output_throughput": 751.7477893491538,
|
|
"total_throughput": 2957.6482460792745,
|
|
"mean_ttft_ms": 26.531575095374137,
|
|
"p50_ttft_ms": 24.292025598697364,
|
|
"p99_ttft_ms": 41.29285377450287,
|
|
"mean_tpot_ms": 5.007692315964597,
|
|
"p50_tpot_ms": 4.998277087638343,
|
|
"p99_tpot_ms": 5.130429720718591,
|
|
"mean_e2e_ms": 392.14430282171816,
|
|
"p50_e2e_ms": 400.28460952453315,
|
|
"p99_e2e_ms": 625.0063395127652,
|
|
"errors": []
|
|
},
|
|
{
|
|
"concurrency": 16,
|
|
"num_prompts": 500,
|
|
"duration_s": 14.20007478701882,
|
|
"success_count": 500,
|
|
"fail_count": 0,
|
|
"input_tokens": 108545,
|
|
"output_tokens": 36529,
|
|
"total_tokens": 145074,
|
|
"request_throughput": 35.21108215972787,
|
|
"input_throughput": 7643.973826055324,
|
|
"output_throughput": 2572.451240425399,
|
|
"total_throughput": 10216.425066480724,
|
|
"mean_ttft_ms": 31.879239567089826,
|
|
"p50_ttft_ms": 28.826430439949036,
|
|
"p99_ttft_ms": 74.12134333979331,
|
|
"mean_tpot_ms": 5.771187238080647,
|
|
"p50_tpot_ms": 5.76495784573639,
|
|
"p99_tpot_ms": 6.1421910060182805,
|
|
"mean_e2e_ms": 447.76513252267614,
|
|
"p50_e2e_ms": 459.7155440133065,
|
|
"p99_e2e_ms": 669.6232496039011,
|
|
"errors": []
|
|
},
|
|
{
|
|
"concurrency": 64,
|
|
"num_prompts": 500,
|
|
"duration_s": 7.960247536888346,
|
|
"success_count": 500,
|
|
"fail_count": 0,
|
|
"input_tokens": 108545,
|
|
"output_tokens": 36583,
|
|
"total_tokens": 145128,
|
|
"request_throughput": 62.81211704572815,
|
|
"input_throughput": 13635.882489457124,
|
|
"output_throughput": 4595.711355767746,
|
|
"total_throughput": 18231.59384522487,
|
|
"mean_ttft_ms": 73.04830395104364,
|
|
"p50_ttft_ms": 53.465207340195775,
|
|
"p99_ttft_ms": 252.97995713772252,
|
|
"mean_tpot_ms": 12.42267764661875,
|
|
"p50_tpot_ms": 12.61188557741512,
|
|
"p99_tpot_ms": 13.063075978620708,
|
|
"mean_e2e_ms": 968.1061067078263,
|
|
"p50_e2e_ms": 967.5668340642005,
|
|
"p99_e2e_ms": 1512.9108975501729,
|
|
"errors": []
|
|
},
|
|
{
|
|
"concurrency": 128,
|
|
"num_prompts": 500,
|
|
"duration_s": 7.319521516095847,
|
|
"success_count": 500,
|
|
"fail_count": 0,
|
|
"input_tokens": 108545,
|
|
"output_tokens": 36613,
|
|
"total_tokens": 145158,
|
|
"request_throughput": 68.31047615619204,
|
|
"input_throughput": 14829.52126874773,
|
|
"output_throughput": 5002.102927013319,
|
|
"total_throughput": 19831.62419576105,
|
|
"mean_ttft_ms": 145.49234842788428,
|
|
"p50_ttft_ms": 90.75760398991406,
|
|
"p99_ttft_ms": 423.2492828951217,
|
|
"mean_tpot_ms": 22.034148180580335,
|
|
"p50_tpot_ms": 23.052740126916806,
|
|
"p99_tpot_ms": 23.587740010073134,
|
|
"mean_e2e_ms": 1730.9650285840034,
|
|
"p50_e2e_ms": 1733.5386699996889,
|
|
"p99_e2e_ms": 2722.885905068833,
|
|
"errors": []
|
|
}
|
|
]
|
|
} |