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

8
llama_stack/providers/inline/eval/meta_reference/eval.py
View file

@ -14,8 +14,8 @@ from llama_stack.apis.datasetio import DatasetIO
from llama_stack.apis.datasets import Datasets
from llama_stack.apis.inference import (
Inference,
OpenAIChatCompletionRequest,
OpenAICompletionRequest,
OpenAIChatCompletionRequestWithExtraBody,
OpenAICompletionRequestWithExtraBody,
OpenAISystemMessageParam,
OpenAIUserMessageParam,
UserMessage,
@ -175,7 +175,7 @@ class MetaReferenceEvalImpl(
sampling_params["stop"] = candidate.sampling_params.stop
input_content = json.loads(x[ColumnName.completion_input.value])
params = OpenAICompletionRequest(
params = OpenAICompletionRequestWithExtraBody(
model=candidate.model,
prompt=input_content,
**sampling_params,
@ -195,7 +195,7 @@ class MetaReferenceEvalImpl(
messages += [OpenAISystemMessageParam(**x) for x in chat_completion_input_json if x["role"] == "system"]
messages += input_messages
params = OpenAIChatCompletionRequest(
params = OpenAIChatCompletionRequestWithExtraBody(
model=candidate.model,
messages=messages,
**sampling_params,