Minor bugfix on benchmark serving (#1005)
This commit is contained in:
@@ -195,7 +195,8 @@ async def async_request_openai_completions(
|
|||||||
output.ttft = ttft
|
output.ttft = ttft
|
||||||
|
|
||||||
# Decoding phase
|
# Decoding phase
|
||||||
output.itl.append(timestamp - most_recent_timestamp)
|
else:
|
||||||
|
output.itl.append(timestamp - most_recent_timestamp)
|
||||||
|
|
||||||
most_recent_timestamp = timestamp
|
most_recent_timestamp = timestamp
|
||||||
generated_text += data["choices"][0]["text"]
|
generated_text += data["choices"][0]["text"]
|
||||||
|
|||||||
Reference in New Issue
Block a user