phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-08 21:04:39 +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

13
benchmarking/k8s-benchmark/stack-k8s.yaml.template
View file

@ -52,9 +52,20 @@ spec:
value: http://vllm-server-safety.default.svc.cluster.local:8001/v1
- name: VLLM_TLS_VERIFY
value: "false"
command: ["python", "-m", "llama_stack.core.server.server", "/etc/config/stack_run_config.yaml", "--port", "8323"]
- name: LLAMA_STACK_LOGGING
value: "all=WARNING"
- name: LLAMA_STACK_CONFIG
value: "/etc/config/stack_run_config.yaml"
- name: LLAMA_STACK_WORKERS
value: "${LLAMA_STACK_WORKERS}"
command: ["uvicorn", "llama_stack.core.server.server:create_app", "--host", "0.0.0.0", "--port", "8323", "--workers", "$LLAMA_STACK_WORKERS", "--factory"]
ports:
- containerPort: 8323
resources:
requests:
cpu: "${LLAMA_STACK_WORKERS}"
limits:
cpu: "${LLAMA_STACK_WORKERS}"
volumeMounts:
- name: llama-storage
mountPath: /root/.llama