phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 21:48:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

featu: support passing "extra body" throught to providers

Browse source 
# What does this PR do?
Allows passing through extra_body parameters to inference providers.


closes #2720

## Test Plan
CI and added new test
This commit is contained in:
Eric Huang 2025-10-10 14:05:16 -07:00
parent cb7fb0705b
commit d7b57a8dd2
4 changed files with 107 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/apis/inference/inference.py
View file

@ -1058,8 +1058,6 @@ class OpenAICompletionRequest(BaseModel):
: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.
:param guided_choice: (Optional) vLLM-specific parameter for guided generation with a list of choices.
:param prompt_logprobs: (Optional) vLLM-specific parameter for number of log probabilities to return for prompt tokens.
"""
model_config = ConfigDict(extra="allow")
@ -1082,12 +1080,6 @@ class OpenAICompletionRequest(BaseModel):
temperature: float | None = None
top_p: float | None = None
user: str | None = None
# vLLM-specific parameters (documented here but also allowed via extra fields)
guided_choice: list[str] | None = None
prompt_logprobs: int | None = None
# for fill-in-the-middle type completion
suffix: str | None = None