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

[diffusion] fix: guard sage attention sm90 bindings (#34107)

Browse Source 
Co-authored-by: RunFMe <RunFMe@users.noreply.github.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
This commit is contained in:
Gregory Leleytner
2026-08-08 21:32:40 +08:00
committed by GitHub
co-authored by RunFMe Mick
parent db75dfe10f
commit 548ff545c5
3 changed files with 53 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/sglang-diffusion/attention_backends.mdx
+2 -2
View File
@@ -57,7 +57,7 @@ For SGLang-native pipelines, the CLI accepts the lowercase names of `AttentionBa
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`sage_attn`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)", whiteSpace: "nowrap"}}>`SAGE_ATTN`</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Requires <code>sageattention</code>. Upstream SageAttention CUDA extensions target SM80/SM86/SM89/SM90/SM120 (compute capability 8.0/8.6/8.9/9.0/12.0); see upstream <code>setup.py</code>: https://github.com/thu-ml/SageAttention/blob/main/setup.py.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Requires <code>sageattention</code>. On Hopper (SM90), PyPI <code>sageattention==2.2.0</code> is unsupported because it lacks the upstream SM90 binding fix. Install <code>pip install --force-reinstall git+https://github.com/thu-ml/SageAttention.git@d9704247a5139ab4c03bf7fc6b35cc0e2cbb5ea4 --no-build-isolation</code>. Upstream SageAttention CUDA extensions target SM80/SM86/SM89/SM90/SM120; see upstream <code>setup.py</code>.</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`sage_attn_3`</td>
@@ -401,7 +401,7 @@ Some backends require additional configuration. You can pass these parameters vi
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>Yes</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>❌</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Optional dependency on CUDA and MUSA. Falls back to FlashAttention if <code>sageattention</code> is not installed.</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Optional dependency on CUDA and MUSA. On Hopper, also falls back to FlashAttention when the installed package lacks the SM90 binding fix.</td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>`sage_attn_3`</td>