phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 23:50:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

apis, alt

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-05-18 21:20:00 -07:00
parent c7015d3d60
commit 3bc175320b
15 changed files with 1356 additions and 869 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -28,7 +28,7 @@ from llama_stack.apis.inference import (
CompletionRequest,
CompletionResponse,
CompletionResponseStreamChunk,
Inference,
InferenceProvider,
InterleavedContent,
LogProbConfig,
Message,
@ -86,7 +86,7 @@ class MetaReferenceInferenceImpl(
OpenAICompletionToLlamaStackMixin,
OpenAIChatCompletionToLlamaStackMixin,
SentenceTransformerEmbeddingMixin,
Inference,
InferenceProvider,
ModelsProtocolPrivate,
):
def __init__(self, config: MetaReferenceInferenceConfig) -> None:

4
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -9,7 +9,7 @@ from collections.abc import AsyncGenerator
from llama_stack.apis.inference import (
CompletionResponse,
Inference,
InferenceProvider,
InterleavedContent,
LogProbConfig,
Message,
@ -38,7 +38,7 @@ class SentenceTransformersInferenceImpl(
OpenAIChatCompletionToLlamaStackMixin,
OpenAICompletionToLlamaStackMixin,
SentenceTransformerEmbeddingMixin,
Inference,
InferenceProvider,
ModelsProtocolPrivate,
):
def __init__(self, config: SentenceTransformersInferenceConfig) -> None: