phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-30 11:50:14 +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

3
llama_stack/apis/inference/inference.py
View file

@ -1038,6 +1038,8 @@ class InferenceProvider(Protocol):
# vLLM-specific parameters
guided_choice: list[str] | None = None,
prompt_logprobs: int | None = None,
# for fill-in-the-middle type completion
suffix: str | None = None,
) -> OpenAICompletion:
"""Generate an OpenAI-compatible completion for the given prompt using the specified model.
@ -1058,6 +1060,7 @@ class InferenceProvider(Protocol):
:param temperature: (Optional) The temperature to use.
:param top_p: (Optional) The top p to use.
:param user: (Optional) The user to use.
:param suffix: (Optional) The suffix that should be appended to the completion.
:returns: An OpenAICompletion.
"""
...