minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

sync attention doc and ep doc to doctree (#14257)

Browse Source 
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
This commit is contained in:
b8zhong
2025-12-01 21:15:22 -08:00
committed by GitHub
co-authored by Brayden Zhong
parent c9e2090101
commit e6420100ee
5 changed files with 10 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/advanced_features/attention_backend.md
+2 -2
View File
@@ -17,7 +17,7 @@ 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)** | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
| **Triton** | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ |
| **Torch Native (SDPA)** | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ |
| **FlexAttention (PyTorch)** | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
@@ -33,7 +33,7 @@ The support matrix is split into two parts: MHA (standard attention) and MLA (mu
| **Backend** | **Native Page Sizes** | **FP8 KV Cache** | **Chunked Prefix Cache** | **Spec topk=1** | **Spec topk>1** |
|----------------------------|---------------------------|------------------|--------------------------|-----------------|-----------------|
| **FlashInfer MLA** | 1 | ❌ | ✅ | ✅ | ❌ |
| **FlashMLA** | 64 | ❌ | ✅ | ✅ | ❌ |
| **FlashMLA** | 64 | ✅ | ✅ | ✅ | ❌ |
| **Cutlass MLA** | 128 | ✅ | ✅ | ✅ | ❌ |
| **TRTLLM MLA (Blackwell)** | 32 or 64 | ✅ | ✅ | ✅ | ❌ |
| **FA3 (FlashAttention 3)** | n/a | ❌ | ✅ | ✅ | ⚠️ (page_size=1 only) |