[Fix] Reduce busy polling when scheduler is idle (#6026)

This commit is contained in:
Povilas Kanapickas
2025-06-13 00:58:22 +03:00
committed by GitHub
parent 4b9971e401
commit bd7cfbd2f8
5 changed files with 48 additions and 1 deletions

View File

@@ -107,7 +107,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| `--download-dir` | Model download directory for huggingface. | None |
| `--base-gpu-id` | The base GPU ID to start allocating GPUs from. Useful when running multiple instances on the same machine. | 0 |
| `--gpu-id-step` | The delta between consecutive GPU IDs that are used. For example, setting it to 2 will use GPU 0,2,4,.... | 1 |
| `--sleep-on-idle` | Reduce CPU usage when sglang is idle. | False |
## Logging