biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ROCm] Add stablelm Head Size 80 To Supported Head Sizes For ROCM_ATTN (#35527)

Browse Source 
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
This commit is contained in:
Micah Williamson
2026-02-27 22:16:34 -06:00
committed by GitHub
parent d5b6f3ba36
commit 0edf101d2b
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/design/attention_backends.md
View File

@@ -172,7 +172,7 @@ Priority is **1 = highest** (tried first).
| `FLEX_ATTENTION` | | fp16, bf16, fp32 | `auto`, `bfloat16` | Any | Any | ❌ | ✅ | ❌ | Decoder, Encoder Only | Any |
| `ROCM_AITER_FA` | | fp16, bf16 | `auto` | 16, 32 | 64, 128, 256 | ❌ | ❌ | ❌ | Decoder | N/A |
| `ROCM_AITER_UNIFIED_ATTN` | | fp16, bf16 | `auto` | Any | Any | ❌ | ❌ | ❌ | All | N/A |
| `ROCM_ATTN` | | fp16, bf16, fp32 | `auto` | 16, 32, 544 | 32, 64, 96, 128, 160, 192, 224, 256 | ❌ | ❌ | ❌ | All | N/A |
| `ROCM_ATTN` | | fp16, bf16, fp32 | `auto` | 16, 32, 544 | 32, 64, 80, 96, 128, 160, 192, 224, 256 | ❌ | ❌ | ❌ | All | N/A |
| `TREE_ATTN` | | fp16, bf16 | `auto` | %16 | 32, 64, 96, 128, 160, 192, 224, 256 | ❌ | ❌ | ❌ | Decoder | Any |
| `TRITON_ATTN` | | fp16, bf16, fp32 | `auto`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | %16 | Any | ✅ | ✅ | ❌ | All | Any |