phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 06:53:47 +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 5625aef48a
commit ca88f3f182
17 changed files with 63 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/utils/inference/model_registry.py
View file

@ -4,11 +4,11 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Dict, List
from typing import Dict
from llama_models.sku_list import resolve_model
from llama_stack.providers.datatypes import ModelDef, ModelsProtocolPrivate
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
class ModelRegistryHelper(ModelsProtocolPrivate):
@ -28,14 +28,8 @@ class ModelRegistryHelper(ModelsProtocolPrivate):
return self.stack_to_provider_models_map[identifier]
async def register_model(self, model: ModelDef) -> None:
async def register_model(self, model: Model) -> None:
if model.identifier not in self.stack_to_provider_models_map:
raise ValueError(
f"Unsupported model {model.identifier}. Supported models: {self.stack_to_provider_models_map.keys()}"
)
async def list_models(self) -> List[ModelDef]:
models = []
for llama_model, provider_model in self.stack_to_provider_models_map.items():
models.append(ModelDef(identifier=llama_model, llama_model=llama_model))
return models