[ROCm][CI] Reduce Flakiness For test_async_scheduling Using ROCM_ATTN With FP32 (#30811)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
This commit is contained in:
@@ -152,7 +152,11 @@ class RocmAttentionMetadataBuilder(AttentionMetadataBuilder[RocmAttentionMetadat
|
||||
|
||||
class RocmAttentionBackend(AttentionBackend):
|
||||
accept_output_buffer: bool = True
|
||||
supported_dtypes: ClassVar[list[torch.dtype]] = [torch.float16, torch.bfloat16]
|
||||
supported_dtypes: ClassVar[list[torch.dtype]] = [
|
||||
torch.float16,
|
||||
torch.bfloat16,
|
||||
torch.float32,
|
||||
]
|
||||
|
||||
@classmethod
|
||||
def get_supported_head_sizes(cls) -> list[int]:
|
||||
|
||||
Reference in New Issue
Block a user