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 15:40:30 -07:00
parent cb7fb0705b
commit 9f50338a4e
35 changed files with 1892 additions and 199 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -9,7 +9,7 @@ from collections.abc import AsyncIterator
from llama_stack.apis.inference import (
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAIChatCompletionRequest,
OpenAIChatCompletionRequestWithExtraBody,
)
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
@ -31,7 +31,7 @@ class RunpodInferenceAdapter(OpenAIMixin):
async def openai_chat_completion(
self,
params: OpenAIChatCompletionRequest,
params: OpenAIChatCompletionRequestWithExtraBody,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
"""Override to add RunPod-specific stream_options requirement."""
params = params.model_copy()