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

[diffusion] docs: sync snapshot and minimax-h3 subblock features (#38784)

Browse Source 
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
This commit is contained in:
Mick
2026-09-10 17:23:43 +08:00
committed by GitHub
co-authored by Mick Qian
parent 8a6ab89bf0
commit c9c26d56b2
3 changed files with 60 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/sglang-diffusion/attention_backends.mdx
+5
View File
@@ -79,6 +79,11 @@ For SGLang-native pipelines, the CLI accepts the lowercase names of `AttentionBa
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)", whiteSpace: "nowrap"}}>`VIDEO_SPARSE_ATTN`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Requires <code>vsa</code>. Configure <code>sparsity</code> via <code>--attention-backend-config</code>.</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`subblock_sparse_attn`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)", whiteSpace: "nowrap"}}>`SUBBLOCK_SPARSE_ATTN`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Training-free SubBlock sparsity for MiniMax-H3 on CUDA SM90, SM100, and SM120. The default compute mode is BF16; <code>compute_mode=sage_fp8</code> is an approximate SM90-only path that requires <code>SpargeAttn</code>. See the <a href="/cookbook/diffusion/MiniMax/MiniMax-H3#subblock-sparse-attention">MiniMax-H3 recipe</a>.</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`video_sparse_attn_h3`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)", whiteSpace: "nowrap"}}>`VIDEO_SPARSE_ATTN_H3`</td>