chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[diffusion] feat: support SparseVideoGen2 attention backend (#17507)

Browse Source 
Co-authored-by: Mick <mickjagger19@icloud.com>
This commit is contained in:
Xinwei Qiang
2026-02-13 16:20:46 +08:00
committed by GitHub
parent d97eb111a3
commit 356e338607
9 changed files with 732 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/diffusion/performance/attention_backends.md
View File

@@ -29,6 +29,7 @@ For SGLang-native pipelines, the CLI accepts the lowercase names of `AttentionBa
| `video_sparse_attn` | `VIDEO_SPARSE_ATTN` | Requires `vsa`. Configure `sparsity` via `--attention-backend-config`. |
| `vmoba_attn` | `VMOBA_ATTN` | Requires `kernel.attn.vmoba_attn.vmoba`. Configure via `--attention-backend-config`. |
| `aiter` | `AITER` | Requires `aiter`. |
| `sparse_video_gen_2_attn` | `SPARSE_VIDEO_GEN_2_ATTN` | Requires `svg`. See installation instructions at https://github.com/svg-project/Sparse-VideoGen. |
## Selection priority
@@ -92,6 +93,7 @@ Some backends require additional configuration. You can pass these parameters vi
| `video_sparse_attn` | ✅ | ❌ | ❌ | CUDA-only. Requires `vsa`. Configure `sparsity` via `--attention-backend-config`. |
| `vmoba_attn` | ✅ | ❌ | ❌ | CUDA-only. Requires `kernel.attn.vmoba_attn.vmoba`. Configure via `--attention-backend-config`. |
| `aiter` | ✅ | ❌ | ❌ | Requires `aiter`. |
| `sparse_video_gen_2_attn` | ✅ | ❌ | ❌ | CUDA-only. Requires `svg`. |
## Usage