phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 13:57:57 +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 15:05:22 -07:00
parent cb7fb0705b
commit dbaaeea255
21 changed files with 1799 additions and 96 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -4,6 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from collections.abc import AsyncIterator
from typing import Any
from urllib.parse import urljoin
import httpx
@ -94,6 +95,7 @@ class VLLMInferenceAdapter(OpenAIMixin):
async def openai_chat_completion(
self,
params: OpenAIChatCompletionRequest,
**kwargs: Any,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
params = params.model_copy()
@ -108,4 +110,4 @@ class VLLMInferenceAdapter(OpenAIMixin):
if not params.tools and params.tool_choice is not None:
params.tool_choice = ToolChoice.none.value
return await super().openai_chat_completion(params)
return await super().openai_chat_completion(params, **kwargs)