phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-28 15:02:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

cleanup

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-06 17:20:33 -07:00 • committed by Ashwin Bharambe
parent 91e0063593
commit 1550187cd8
1 changed files with 0 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

15
llama_stack/providers/impls/meta_reference/inference/inference.py
View file

@ -31,7 +31,6 @@ class MetaReferenceInferenceImpl(Inference):
if model is None:
raise RuntimeError(f"Unknown model: {config.model}, Run `llama model list`")
self.model = model
self.registered_model_defs = []
# verify that the checkpoint actually is for this model lol
async def initialize(self) -> None:
@ -39,24 +38,10 @@ class MetaReferenceInferenceImpl(Inference):
self.generator.start()
async def register_model(self, model: ModelDef) -> None:
existing = await self.get_model(model.identifier)
if existing is not None:
return
if model.identifier != self.model.descriptor():
raise RuntimeError(
f"Model mismatch: {model.identifier} != {self.model.descriptor()}"
)
self.registered_model_defs = [model]
async def list_models(self) -> List[ModelDef]:
return self.registered_model_defs
async def get_model(self, identifier: str) -> Optional[ModelDef]:
for model in self.registered_model_defs:
if model.identifier == identifier:
return model
return None
async def shutdown(self) -> None:
self.generator.stop()