EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Rename flashmla kernel options of nsa backend for better readability (#11876)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-10-21 15:14:16 -05:00
committed by GitHub
parent ebff4ee648
commit ef4a8097b8
3 changed files with 31 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/advanced_features/server_arguments.md
View File

@@ -228,6 +228,8 @@ Please consult the documentation below and [server_args.py](https://github.com/s
| `--sampling-backend` | Choose the kernels for sampling layers. | None |
| `--grammar-backend` | Choose the backend for grammar-guided decoding. | None |
| `--mm-attention-backend` | Set multimodal attention backend. | None |
| `--nsa-prefill-backend` | Prefill attention implementation for nsa backend. | `flashmla_sparse` |
| `--nsa-decode-backend` | Decode attention implementation for nsa backend. | `flashmla_kv` |
## Speculative decoding