llama-stack-mirror/benchmarking
Eric Huang a285f9c95f chore: refactor server.main
# 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.
2025-09-17 12:29:49 -07:00
..
k8s-benchmark chore: refactor server.main 2025-09-17 12:29:49 -07:00