artifacts/mtp-g128-chanhead/benchmark.jsonl

{"backend": "vllm-chat", "dataset_name": "sharegpt", "request_rate": Infinity, "max_concurrency": 1, "sharegpt_output_len": 512, "random_input_len": 1024, "random_output_len": 1024, "random_range_ratio": 0.0, "duration": 265.0641822250002, "completed": 128, "total_input_tokens": 33688, "total_output_tokens": 65536, "total_output_tokens_retokenized": 65191, "request_throughput": 0.4829019104940666, "input_throughput": 127.09374656815714, "output_throughput": 247.2457781729621, "mean_e2e_latency_ms": 2070.4879705312537, "median_e2e_latency_ms": 2039.3644189999804, "std_e2e_latency_ms": 287.2436109815991, "p99_e2e_latency_ms": 2754.8550399299597, "mean_ttft_ms": 2070.4879705312537, "median_ttft_ms": 2039.3644189999804, "std_ttft_ms": 287.2436109815991, "p99_ttft_ms": 2754.8550399299597, "mean_tpot_ms": 0.0, "median_tpot_ms": 0.0, "std_tpot_ms": 0.0, "p99_tpot_ms": 0.0, "mean_itl_ms": 0.0, "median_itl_ms": 0.0, "std_itl_ms": 0.0, "p95_itl_ms": 0.0, "p99_itl_ms": 0.0, "concurrency": 0.999842596624525, "accept_length": null}