Minor bugfix on benchmark serving (#1005)

This commit is contained in:
Roger Wang
2024-08-09 09:53:50 -07:00
committed by GitHub
parent b568df5d03
commit 05c50a82b8

View File

@@ -195,7 +195,8 @@ async def async_request_openai_completions(
output.ttft = ttft
# Decoding phase
output.itl.append(timestamp - most_recent_timestamp)
else:
output.itl.append(timestamp - most_recent_timestamp)
most_recent_timestamp = timestamp
generated_text += data["choices"][0]["text"]