mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
Update docs/docs/distributions/starting_llama_stack_server.mdx
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
parent
2f2c7f4305
commit
5fd4e52b01
1 changed files with 1 additions and 1 deletions
|
|
@ -42,7 +42,7 @@ Configure Gunicorn behavior using environment variables:
|
||||||
- `GUNICORN_KEEPALIVE`: Connection keepalive in seconds (default: `5`)
|
- `GUNICORN_KEEPALIVE`: Connection keepalive in seconds (default: `5`)
|
||||||
- `GUNICORN_MAX_REQUESTS`: Restart workers after N requests to prevent memory leaks (default: `10000`)
|
- `GUNICORN_MAX_REQUESTS`: Restart workers after N requests to prevent memory leaks (default: `10000`)
|
||||||
- `GUNICORN_MAX_REQUESTS_JITTER`: Randomize worker restart timing (default: `1000`)
|
- `GUNICORN_MAX_REQUESTS_JITTER`: Randomize worker restart timing (default: `1000`)
|
||||||
- `GUNICORN_PRELOAD`: Preload app before forking workers for memory efficiency (default: `true`)
|
- `GUNICORN_PRELOAD`: Preload app before forking workers for memory efficiency (default: `true`, as set in `run.py` line 264)
|
||||||
|
|
||||||
**Important**: When using multiple workers without `GUNICORN_PRELOAD=true`, you may encounter database initialization race conditions. To avoid this, set `GUNICORN_PRELOAD=true` and install all dependencies with `uv sync --group unit --group test`.
|
**Important**: When using multiple workers without `GUNICORN_PRELOAD=true`, you may encounter database initialization race conditions. To avoid this, set `GUNICORN_PRELOAD=true` and install all dependencies with `uv sync --group unit --group test`.
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue