diff --git a/tests/v1/spec_decode/test_acceptance_length.py b/tests/v1/spec_decode/test_acceptance_length.py index 176716e9e..7276688f4 100644 --- a/tests/v1/spec_decode/test_acceptance_length.py +++ b/tests/v1/spec_decode/test_acceptance_length.py @@ -88,6 +88,8 @@ def get_available_attention_backends() -> list[str]: get_valid_backends = getattr(current_platform.__class__, "get_valid_backends", None) if get_valid_backends is None: if current_platform.is_rocm(): + # ROCm uses Triton as its default attention backend since + # Flash Attention is not supported. return ["TRITON_ATTN"] else: return ["FLASH_ATTN"]