phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-21 11:48:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

resource oriented object design for models

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-07 16:43:55 -08:00
parent 0297111dfd
commit 9076221924
17 changed files with 64 additions and 86 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/distribution/routers/routers.py
View file

@ -70,7 +70,7 @@ class InferenceRouter(Inference):
async def shutdown(self) -> None:
pass
async def register_model(self, model: ModelDef) -> None:
async def register_model(self, model: Model) -> None:
await self.routing_table.register_model(model)
async def chat_completion(

13
llama_stack/distribution/routers/routing_tables.py
View file

@ -78,12 +78,7 @@ class CommonRoutingTableImpl(RoutingTable):
# Register all objects from providers
for pid, p in self.impls_by_provider_id.items():
api = get_impl_api(p)
if api == Api.inference:
p.model_store = self
models = await p.list_models()
await add_objects(models, pid, ModelDefWithProvider)
elif api == Api.memory:
if api == Api.memory:
p.memory_bank_store = self
memory_banks = await p.list_memory_banks()
await add_objects(memory_banks, pid, None)
@ -185,13 +180,13 @@ class CommonRoutingTableImpl(RoutingTable):
class ModelsRoutingTable(CommonRoutingTableImpl, Models):
async def list_models(self) -> List[ModelDefWithProvider]:
async def list_models(self) -> List[Model]:
return await self.get_all_with_type("model")
async def get_model(self, identifier: str) -> Optional[ModelDefWithProvider]:
async def get_model(self, identifier: str) -> Optional[Model]:
return await self.get_object_by_identifier(identifier)
async def register_model(self, model: ModelDefWithProvider) -> None:
async def register_model(self, model: Model) -> None:
await self.register_object(model)