mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-09 21:18:38 +00:00
Merge 1e891489a8
into sapling-pr-archive-ehhuang
This commit is contained in:
commit
5025e02d81
13 changed files with 170 additions and 4 deletions
|
@ -1106,6 +1106,7 @@ class InferenceProvider(Protocol):
|
|||
top_logprobs: int | None = None,
|
||||
top_p: float | None = None,
|
||||
user: str | None = None,
|
||||
**kwargs: Any,
|
||||
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
|
||||
"""Create chat completions.
|
||||
|
||||
|
@ -1134,6 +1135,7 @@ class InferenceProvider(Protocol):
|
|||
:param top_logprobs: (Optional) The top log probabilities to use.
|
||||
:param top_p: (Optional) The top p to use.
|
||||
:param user: (Optional) The user to use.
|
||||
:param kwargs: (Optional) Additional provider-specific parameters to pass through as extra_body (e.g., chat_template_kwargs for vLLM).
|
||||
:returns: An OpenAIChatCompletion.
|
||||
"""
|
||||
...
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue