phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-10 21:34:36 +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

2
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -102,6 +102,7 @@ class VLLMInferenceAdapter(OpenAIMixin):
top_logprobs: int | None = None,
top_p: float | None = None,
user: str | None = None,
**kwargs: Any,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
max_tokens = max_tokens or self.config.max_tokens
@ -136,4 +137,5 @@ class VLLMInferenceAdapter(OpenAIMixin):
top_logprobs=top_logprobs,
top_p=top_p,
user=user,
**kwargs,
)