phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 05:54:38 +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 15:42:51 -07:00
parent cb7fb0705b
commit 0ed59497bc
35 changed files with 1893 additions and 200 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -14,7 +14,7 @@ from pydantic import ConfigDict
from llama_stack.apis.inference import (
OpenAIChatCompletion,
OpenAIChatCompletionRequest,
OpenAIChatCompletionRequestWithExtraBody,
ToolChoice,
)
from llama_stack.log import get_logger
@ -93,7 +93,7 @@ class VLLMInferenceAdapter(OpenAIMixin):
async def openai_chat_completion(
self,
params: OpenAIChatCompletionRequest,
params: OpenAIChatCompletionRequestWithExtraBody,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
params = params.model_copy()