phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 23:41:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: chat completion with more than one choice

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-05-27 13:56:43 -07:00
parent 484abe3116
commit d4b0b46275
2 changed files with 53 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -1402,9 +1402,8 @@ class OpenAIChatCompletionToLlamaStackMixin:
outstanding_responses: list[Awaitable[AsyncIterator[ChatCompletionResponseStreamChunk]]],
):
id = f"chatcmpl-{uuid.uuid4()}"
for outstanding_response in outstanding_responses:
for i, outstanding_response in enumerate(outstanding_responses):
response = await outstanding_response
i = 0
async for chunk in response:
event = chunk.event
finish_reason = _convert_stop_reason_to_openai_finish_reason(event.stop_reason)
@ -1459,7 +1458,6 @@ class OpenAIChatCompletionToLlamaStackMixin:
model=model,
object="chat.completion.chunk",
)
i = i + 1
async def _process_non_stream_response(
self, model: str, outstanding_responses: list[Awaitable[ChatCompletionResponse]]