minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[6/N] (Elastic EP) Recover failed ranks (#15771)

Browse Source
This commit is contained in:
Xun Sun
2026-04-28 00:44:26 -07:00
committed by GitHub
parent b8a2dcd300
commit 9a53ab3d6d
8 changed files with 337 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/server_arguments.md
+1
View File
@@ -332,6 +332,7 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| `--elastic-ep-backend` | Specify the collective communication backend for elastic EP. Currently supports 'mooncake'. | `none` | `none`, `mooncake` |
| `--enable-elastic-expert-backup` | Enable elastic EP backend to backup expert weights in DRAM feature. Currently supports 'mooncake'.| `False` | bool flag (set to enable) |
| `--mooncake-ib-device` | The InfiniBand devices for Mooncake Backend transfer, accepts multiple comma-separated devices (e.g., --mooncake-ib-device mlx5_0,mlx5_1). Default is None, which triggers automatic device detection when Mooncake Backend is enabled. | `None` | Type: str |
| `--elastic-ep-rejoin` | Indicates that this process is a relaunched elastic EP rank that should rejoin an existing process group during rank recovery. | `False` | bool flag (set to enable) |
## Mamba Cache
| Argument | Description | Defaults | Options |