phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-10 13:28:40 +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 13:54:19 -07:00
parent 96886afaca
commit 521009048a
207 changed files with 71733 additions and 2042 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/passthrough/passthrough.py
View file

@ -100,6 +100,7 @@ class PassthroughInferenceAdapter(Inference):
guided_choice: list[str] | None = None,
prompt_logprobs: int | None = None,
suffix: str | None = None,
**kwargs: Any,
) -> OpenAICompletion:
client = self._get_client()
model_obj = await self.model_store.get_model(model)
@ -124,6 +125,7 @@ class PassthroughInferenceAdapter(Inference):
user=user,
guided_choice=guided_choice,
prompt_logprobs=prompt_logprobs,
**kwargs,
)
return await client.inference.openai_completion(**params)
@ -153,6 +155,7 @@ class PassthroughInferenceAdapter(Inference):
top_logprobs: int | None = None,
top_p: float | None = None,
user: str | None = None,
**kwargs: Any,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
client = self._get_client()
model_obj = await self.model_store.get_model(model)
@ -181,6 +184,7 @@ class PassthroughInferenceAdapter(Inference):
top_logprobs=top_logprobs,
top_p=top_p,
user=user,
**kwargs,
)
return await client.inference.openai_chat_completion(**params)