diff --git a/vllm/entrypoints/llm.py b/vllm/entrypoints/llm.py index 6eb838fa02e3..6c2e87416b94 100644 --- a/vllm/entrypoints/llm.py +++ b/vllm/entrypoints/llm.py @@ -1394,7 +1394,9 @@ def _run_engine( pbar.postfix = ( f"est. speed input: {in_spd:.2f} toks/s, " f"output: {out_spd:.2f} toks/s") - pbar.update(1) + pbar.update(len(output.outputs)) + else: + pbar.update(1) if use_tqdm: pbar.close()