phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

minor fix

Browse source
This commit is contained in:
Swapna Lekkala 2025-09-11 16:10:23 -07:00
parent f9348a6bdf
commit 4271f7352e
1 changed files with 4 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -1417,10 +1417,9 @@ class OpenAIChatCompletionToLlamaStackMixin:
if stream: if stream:
return OpenAIChatCompletionToLlamaStackMixin._process_stream_response(self, model, outstanding_responses) return OpenAIChatCompletionToLlamaStackMixin._process_stream_response(self, model, outstanding_responses)
response = await OpenAIChatCompletionToLlamaStackMixin._process_non_stream_response( return await OpenAIChatCompletionToLlamaStackMixin._process_non_stream_response(
self, model, outstanding_responses self, model, outstanding_responses
) )
return response
async def _process_stream_response( async def _process_stream_response(
self, self,
@ -1512,11 +1511,9 @@ class OpenAIChatCompletionToLlamaStackMixin:
) )
choices.append(choice) choices.append(choice)
usage = None usage = OpenAIChatCompletionUsage(
if total_tokens > 0: prompt_tokens=total_prompt_tokens, completion_tokens=total_completion_tokens, total_tokens=total_tokens
usage = OpenAIChatCompletionUsage( )
prompt_tokens=total_prompt_tokens, completion_tokens=total_completion_tokens, total_tokens=total_tokens
)
return OpenAIChatCompletion( return OpenAIChatCompletion(
id=f"chatcmpl-{uuid.uuid4()}", id=f"chatcmpl-{uuid.uuid4()}",