phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Split off meta-reference-quantized provider

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-10 15:54:08 -07:00
parent 7ff5800dea
commit 1ff0476002
10 changed files with 54 additions and 58 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -17,7 +17,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_messages,
)
from .config import MetaReferenceImplConfig
from .config import MetaReferenceInferenceConfig
from .model_parallel import LlamaModelParallelGenerator
# there's a single model parallel process running serving the model. for now,
@ -26,7 +26,7 @@ SEMAPHORE = asyncio.Semaphore(1)
class MetaReferenceInferenceImpl(Inference, ModelsProtocolPrivate):
def __init__(self, config: MetaReferenceImplConfig) -> None:
def __init__(self, config: MetaReferenceInferenceConfig) -> None:
self.config = config
model = resolve_model(config.model)
if model is None: