[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:
Jack Hu
2026-10-15 17:10:14 -07:00
committed by GitHub
co-authored by Douglas Lehr
parent af28c171f5
commit ef38e8d006
23 changed files with 701 additions and 205 deletions
@@ -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