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

refactor FAKE transfer backend and remove --disaggregation-decode-enable-fake-auto parameter (#18345)

Browse Source
This commit is contained in:
Estrella-xx
2026-02-16 17:27:02 +03:00
committed by GitHub
parent c1d1337afc
commit 1b3513a7e4
10 changed files with 29 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/server_arguments.md
-1
View File
@@ -495,7 +495,6 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| `--disaggregation-prefill-pp` | Prefill pp size. If not set, it is default to 1. This is only set on the decode server. | `1` | Type: int |
| `--disaggregation-ib-device` | The InfiniBand devices for disaggregation transfer, accepts single device (e.g., --disaggregation-ib-device mlx5_0) or multiple comma-separated devices (e.g., --disaggregation-ib-device mlx5_0,mlx5_1). Default is None, which triggers automatic device detection when mooncake backend is enabled. | `None` | Type: str |
| `--disaggregation-decode-enable-offload-kvcache` | Enable async KV cache offloading on decode server (PD mode). | `False` | bool flag (set to enable) |
| `--disaggregation-decode-enable-fake-auto` | Auto enable FAKE mode for decode node testing, no need to pass bootstrap_host and bootstrap_room in request. | `False` | bool flag (set to enable) |
| `--num-reserved-decode-tokens` | Number of decode tokens that will have memory reserved when adding new request to the running batch. | `512` | Type: int |
| `--disaggregation-decode-polling-interval` | The interval to poll requests in decode server. Can be set to >1 to reduce the overhead of this. | `1` | Type: int |