phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: refactor server.main

Browse source 
# What does this PR do?
Refactor main to split out the app construction so that we can use `uvicorn --workers` to enable multi-process stack.


## Test Plan
CI

> uv run --with llama-stack python -m llama_stack.core.server.server benchmarking/k8s-benchmark/stack_run_config.yaml

works.

> LLAMA_STACK_CONFIG=benchmarking/k8s-benchmark/stack_run_config.yaml uv run uvicorn llama_stack.core.server.server:create_app --port 8321 --workers 4

works.
This commit is contained in:
Eric Huang 2025-09-17 12:24:13 -07:00
parent ac1414b571
commit a285f9c95f
7 changed files with 233 additions and 146 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/core/library_client.py
View file

@ -40,7 +40,7 @@ from llama_stack.core.request_headers import (
from llama_stack.core.resolver import ProviderRegistry
from llama_stack.core.server.routes import RouteImpls, find_matching_route, initialize_route_impls
from llama_stack.core.stack import (
construct_stack,
Stack,
get_stack_run_config_from_distro,
replace_env_vars,
)
@ -252,7 +252,10 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
try:
self.route_impls = None
self.impls = await construct_stack(self.config, self.custom_provider_registry)
stack = Stack(self.config, self.custom_provider_registry)
await stack.initialize()
self.impls = stack.impls
except ModuleNotFoundError as _e:
cprint(_e.msg, color="red", file=sys.stderr)
cprint(
@ -289,6 +292,7 @@ class AsyncLlamaStackAsLibraryClient(AsyncLlamaStackClient):
)
raise _e
assert self.impls is not None
if Api.telemetry in self.impls:
setup_logger(self.impls[Api.telemetry])