phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

fix(utils.py): fix streaming to not return usage dict

Browse source 
Fixes https://github.com/BerriAI/litellm/issues/3237
This commit is contained in:
Krrish Dholakia 2024-04-24 08:06:07 -07:00
parent 70c98617da
commit 48c2c3d78a
24 changed files with 107 additions and 83 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/vllm.py
View file

@ -104,7 +104,7 @@ def completion(
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
)
model_response.usage = usage
setattr(model_response, "usage", usage)
return model_response
@ -186,7 +186,7 @@ def batch_completions(
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
)
model_response.usage = usage
setattr(model_response, "usage", usage)
final_outputs.append(model_response)
return final_outputs