[CI][AMD] Gate Aiter MHA FA on dtype (#60679)

Signed-off-by: Ryan Rock <ryan.rock@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
This commit is contained in:
Ryan Rock
2026-10-13 18:55:19 -05:00
committed by GitHub
co-authored by Micah Williamson
parent 7a9d3db896
commit f43d7e1a0f
+5 -1
View File
@@ -887,7 +887,11 @@ class RocmPlatform(Platform):
from vllm._aiter_ops import rocm_aiter_ops
if rocm_aiter_ops.is_mha_enabled() and on_cdna():
if (
rocm_aiter_ops.is_mha_enabled()
and on_cdna()
and (dtype == torch.float16 or dtype == torch.bfloat16)
):
logger.info_once("Using AITER Flash Attention backend for ViT model.")
return AttentionBackendEnum.ROCM_AITER_FA