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

[ROCm][CI] Fix ROCm attention backend validation for head sizes, block sizes, and compute capability checks (#36292)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2026-03-09 12:02:41 -05:00
committed by GitHub
parent 55d27cca55
commit c174d54f86
7 changed files with 55 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/design/attention_backends.md
View File

@@ -213,4 +213,4 @@ configuration.
| `ROCM_AITER_MLA` | fp16, bf16 | `auto`, `bfloat16`, `fp8`, `fp8_e4m3`, `fp8_e5m2` | 1 | Any | ❌ | ❌ | ❌ | ❌ | Decoder | N/A |
| `ROCM_AITER_MLA_SPARSE` | fp16, bf16 | `auto`, `bfloat16` | 1 | Any | ❌ | ✅ | ❌ | ❌ | Decoder | N/A |
| `ROCM_AITER_TRITON_MLA` | fp16, bf16 | `auto` | Any | Any | ❌ | ❌ | ❌ | ❌ | Decoder | N/A |
| `TRITON_MLA` | fp16, bf16 | `auto`, `bfloat16` | Any | Any | ❌ | ❌ | ❌ | ✅ | Decoder | Any |
| `TRITON_MLA` | fp16, bf16 | `auto`, `bfloat16` | %16 | Any | ❌ | ❌ | ❌ | ✅ | Decoder | Any |