phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(stores)!: use backend storage references instead of configs

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-16 16:24:31 -07:00
parent b3099d40e2
commit ea9664874d
47 changed files with 893 additions and 696 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/core/routers/__init__.py
View file

@ -6,7 +6,10 @@
from typing import Any
from llama_stack.core.datatypes import AccessRule, RoutedProtocol
from llama_stack.core.datatypes import (
AccessRule,
RoutedProtocol,
)
from llama_stack.core.stack import StackRunConfig
from llama_stack.core.store import DistributionRegistry
from llama_stack.providers.datatypes import Api, RoutingTable
@ -76,9 +79,13 @@ async def get_auto_router_impl(
api_to_dep_impl[dep_name] = deps[dep_api]
# TODO: move pass configs to routers instead
if api == Api.inference and run_config.inference_store:
if api == Api.inference:
inference_ref = run_config.storage.inference
if not inference_ref:
raise ValueError("storage.inference must be configured in run config")
inference_store = InferenceStore(
config=run_config.inference_store,
reference=inference_ref,
policy=policy,
)
await inference_store.initialize()