59 lines
1.9 KiB
JSON
59 lines
1.9 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": 64,
|
|
"num_prompts": 20,
|
|
"dataset": "/data/user1/yy/datasets/ShareGPT_filtered_chat.json",
|
|
"timestamp": "20260705_121218",
|
|
"results": [
|
|
{
|
|
"concurrency": 1,
|
|
"num_prompts": 20,
|
|
"duration_s": 3.1493232590146363,
|
|
"success_count": 20,
|
|
"fail_count": 0,
|
|
"input_tokens": 6132,
|
|
"output_tokens": 456,
|
|
"total_tokens": 6588,
|
|
"request_throughput": 6.350570695704836,
|
|
"input_throughput": 1947.0849753031027,
|
|
"output_throughput": 144.79301186207027,
|
|
"total_throughput": 2091.877987165173,
|
|
"mean_ttft_ms": 55.51949484506622,
|
|
"p50_ttft_ms": 27.64087135437876,
|
|
"p99_ttft_ms": 295.08487760089326,
|
|
"mean_tpot_ms": 4.6249661131817925,
|
|
"p50_tpot_ms": 4.634099831345484,
|
|
"p99_tpot_ms": 4.827384204164935,
|
|
"mean_e2e_ms": 156.8067875574343,
|
|
"p50_e2e_ms": 148.02213886287063,
|
|
"p99_e2e_ms": 406.6163514624348,
|
|
"errors": []
|
|
},
|
|
{
|
|
"concurrency": 4,
|
|
"num_prompts": 20,
|
|
"duration_s": 1.0271000929642469,
|
|
"success_count": 20,
|
|
"fail_count": 0,
|
|
"input_tokens": 6132,
|
|
"output_tokens": 450,
|
|
"total_tokens": 6582,
|
|
"request_throughput": 19.472298889857267,
|
|
"input_throughput": 5970.206839630238,
|
|
"output_throughput": 438.1267250217885,
|
|
"total_throughput": 6408.333564652026,
|
|
"mean_ttft_ms": 82.42244796128944,
|
|
"p50_ttft_ms": 37.77908312622458,
|
|
"p99_ttft_ms": 263.8731326162815,
|
|
"mean_tpot_ms": 5.172366561559164,
|
|
"p50_tpot_ms": 5.150655882704692,
|
|
"p99_tpot_ms": 5.708390201389117,
|
|
"mean_e2e_ms": 193.68963547749445,
|
|
"p50_e2e_ms": 153.2427944475785,
|
|
"p99_e2e_ms": 387.3923780536279,
|
|
"errors": []
|
|
}
|
|
]
|
|
} |