phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 21:18:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-08 13:23:21 -07:00
parent 96886afaca
commit 1e891489a8
13 changed files with 170 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/core/routers/inference.py
View file

@ -277,6 +277,7 @@ class InferenceRouter(Inference):
top_logprobs: int | None = None,
top_p: float | None = None,
user: str | None = None,
**kwargs: Any,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
logger.debug(
f"InferenceRouter.openai_chat_completion: {model=}, {stream=}, {messages=}",
@ -323,6 +324,7 @@ class InferenceRouter(Inference):
top_logprobs=top_logprobs,
top_p=top_p,
user=user,
**kwargs,
)
provider = await self.routing_table.get_provider_impl(model_obj.identifier)
if stream: