Commit a6950aea authored by zhuwenwen's avatar zhuwenwen
Browse files

update benchmark of tht

parent 5c4471ef
...@@ -224,8 +224,15 @@ def main(args: argparse.Namespace): ...@@ -224,8 +224,15 @@ def main(args: argparse.Namespace):
raise ValueError(f"Unknown backend: {args.backend}") raise ValueError(f"Unknown backend: {args.backend}")
total_num_tokens = sum(prompt_len + output_len total_num_tokens = sum(prompt_len + output_len
for _, prompt_len, output_len in requests) for _, prompt_len, output_len in requests)
print(f"Throughput: {len(requests) / elapsed_time:.2f} requests/s, " if args.dataset is None:
total_out_tokens = args.output_len * args.num_prompts
else:
total_out_tokens = sum(output_len for _, _, output_len in requests)
print(f"Latency: {elapsed_time:.2f} s")
print(f"All Throughput: {len(requests) / elapsed_time:.2f} requests/s, "
f"{total_num_tokens / elapsed_time:.2f} tokens/s") f"{total_num_tokens / elapsed_time:.2f} tokens/s")
print(f"Generate Throughput: {total_out_tokens / elapsed_time:.2f} tokens/s")
if __name__ == "__main__": if __name__ == "__main__":
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment