Add longer accuracy test on CI (#1049)

This commit is contained in:
Lianmin Zheng
2024-08-12 02:21:38 -07:00
committed by GitHub
parent 89f23a5178
commit 41598e0d8e
13 changed files with 385 additions and 44 deletions

View File

@@ -669,19 +669,20 @@ async def benchmark(
"backend": args.backend,
"dataset_name": args.dataset_name,
"request_rate": request_rate,
"total_input": metrics.total_input,
"total_output": metrics.total_output,
"total_output_retokenized": metrics.total_output_retokenized,
"mean_e2e_latency": metrics.mean_e2e_latency_ms,
"median_e2e_latency": metrics.median_e2e_latency_ms,
"median_ttft": metrics.median_ttft_ms,
"median_itl": metrics.median_itl_ms,
"output_token_throughput": metrics.output_throughput,
"total_input_tokens": metrics.total_input,
"total_output_tokens": metrics.total_output,
"total_output_tokens_retokenized": metrics.total_output_retokenized,
"mean_e2e_latency_ms": metrics.mean_e2e_latency_ms,
"median_e2e_latency_ms": metrics.median_e2e_latency_ms,
"median_ttft_ms": metrics.median_ttft_ms,
"median_itl_ms": metrics.median_itl_ms,
"output_throughput": metrics.output_throughput,
"sharegpt_output_len": args.sharegpt_output_len,
"random_input_len": args.random_input_len,
"random_output_len": args.random_output_len,
"random_range_ratio": args.random_range_ratio,
"benchmark_duration": benchmark_duration,
"duration": benchmark_duration,
"completed": metrics.completed,
}
else:
print(f"Error running benchmark for request rate: {request_rate}")