phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

migrate model to Resource and new registration signature (#410)

Browse source 
* resource oriented object design for models

* add back llama_model field

* working tests

* register singature fix

* address feedback

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This commit is contained in:
Dinesh Yeduguru 2024-11-08 16:12:57 -08:00 • committed by GitHub
parent bd0622ef10
commit ec644d3418
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 99 additions and 90 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/distribution/routers/routers.py
View file

@ -4,7 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Any, AsyncGenerator, Dict, List
from typing import Any, AsyncGenerator, Dict, List, Optional
from llama_stack.apis.datasetio.datasetio import DatasetIO
from llama_stack.distribution.datatypes import RoutingTable
@ -71,8 +71,16 @@ class InferenceRouter(Inference):
async def shutdown(self) -> None:
pass
async def register_model(self, model: ModelDef) -> None:
await self.routing_table.register_model(model)
async def register_model(
self,
model_id: str,
provider_model_id: Optional[str] = None,
provider_id: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
) -> None:
await self.routing_table.register_model(
model_id, provider_model_id, provider_id, metadata
)
async def chat_completion(
self,