[Model][Hardware][AMD][Kernel] Part 2/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_ATTN (#42755)
Signed-off-by: Jack Hu <Jack.Hu@amd.com> Signed-off-by: Jack Hu <jingxujaster@hotmail.com> Signed-off-by: Jack Hu <jack.hu@amd.com> Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
This commit is contained in:
@@ -531,11 +531,6 @@ class FusedMoEExperts(ABC):
|
||||
def is_monolithic() -> bool:
|
||||
raise NotImplementedError("Implemented by subclasses.")
|
||||
|
||||
@staticmethod
|
||||
def _supports_hash_routing() -> bool:
|
||||
"""Whether a monolithic kernel implements hash routing."""
|
||||
return False
|
||||
|
||||
@property
|
||||
def expects_unquantized_inputs(self) -> bool:
|
||||
"""Whether or not the PrepareFinalize should defer input quantization
|
||||
|
||||
Reference in New Issue
Block a user