[ROCM] Enable aiter attn backend for qwen3-next model (#32492)

Signed-off-by: jennyyyyzhen <yzhen@hmc.edu>
2026-01-31 01:03:57 -08:00
parent f68e3ea4e1
commit 527bcd14d4
2 changed files with 2 additions and 2 deletions
--- a/vllm/v1/attention/backends/rocm_aiter_fa.py
+++ b/vllm/v1/attention/backends/rocm_aiter_fa.py
@@ -683,7 +683,7 @@ class AiterFlashAttentionBackend(AttentionBackend):

    @staticmethod
    def get_supported_kernel_block_sizes() -> list[int | MultipleOf]:
-        return [MultipleOf(16)]
+        return [16, 32]

    @classmethod
    def get_supported_head_sizes(cls) -> list[int]: