phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-02 20:40:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add suffix to openai.completions

Browse source
This commit is contained in:
Hardik Shah 2025-06-13 15:39:45 -07:00
parent e2e15ebb6c
commit 1cfb5b1205
15 changed files with 101 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -426,6 +426,7 @@ class InferenceRouter(Inference):
user: str | None = None,
guided_choice: list[str] | None = None,
prompt_logprobs: int | None = None,
suffix: str | None = None,
) -> OpenAICompletion:
logger.debug(
f"InferenceRouter.openai_completion: {model=}, {stream=}, {prompt=}",
@ -456,6 +457,7 @@ class InferenceRouter(Inference):
user=user,
guided_choice=guided_choice,
prompt_logprobs=prompt_logprobs,
suffix=suffix,
)
provider = self.routing_table.get_provider_impl(model_obj.identifier)