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

Signed-off-by: Micah Williamson <micah.williamson@amd.com>

docs/design/attention_backends.md

@@ -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 |
 

vllm/v1/attention/backends/rocm_attn.py

@@ -182,7 +182,7 @@ class RocmAttentionBackend(AttentionBackend):
 
     @classmethod
     def get_supported_head_sizes(cls) -> list[int]:
-        return [32, 64, 96, 128, 160, 192, 224, 256]
+        return [32, 64, 80, 96, 128, 160, 192, 224, 256]
 
     @classmethod
     def validate_head_size(cls, head_size: int) -> None: