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, recording

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-08 14:56:58 -07:00
parent 16db42e7e5
commit c76bf97ccf
228 changed files with 86861 additions and 64604 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/core/routers/inference.py
View file

@ -201,6 +201,7 @@ class InferenceRouter(Inference):
guided_choice: list[str] | None = None,
prompt_logprobs: int | None = None,
suffix: str | None = None,
**kwargs: Any,
) -> OpenAICompletion:
logger.debug(
f"InferenceRouter.openai_completion: {model=}, {stream=}, {prompt=}",
@ -227,6 +228,7 @@ class InferenceRouter(Inference):
guided_choice=guided_choice,
prompt_logprobs=prompt_logprobs,
suffix=suffix,
**kwargs,
)
provider = await self.routing_table.get_provider_impl(model_obj.identifier)
if stream:
@ -277,6 +279,7 @@ 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 +326,7 @@ 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: