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

add the fa4 mm backend and varlen func (#13539)

Browse Source 
Signed-off-by: vincentzed <207368749+vincentzed@users.noreply.github.com>
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
This commit is contained in:
Yi Zhong
2026-01-23 23:12:06 +08:00
committed by GitHub
co-authored by Brayden Zhong
parent 2fb328109f
commit 08fcda2f63
4 changed files with 58 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/attention_backend.md
+1 -1
View File
@@ -19,7 +19,7 @@ The support matrix is split into two parts: MHA (standard attention) and MLA (mu
|---------------------------------|-----------------------------|------------------|-----------------|-----------------|-----------------|--------------------|----------------|
| **FlashInfer** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ |
| **FA3 (FlashAttention 3)** | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ |
| **FA4 (FlashAttention 4)** | 128 | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| **FA4 (FlashAttention 4)** | 128 | ❌ | ✅ | ❌ | ❌ | ❌ | ✅ |
| **Triton** | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Torch Native (SDPA)** | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ |
| **FlexAttention (PyTorch)** | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |