[Kernel] Integrate CUTLASS MoE kernel with PPLX (#18762)

Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
ElizaWszola
2025-06-06 18:26:11 -07:00
committed by GitHub
co-authored by Tyler Michael Smith
parent 6e0cd10f72
commit 84166fee97
26 changed files with 917 additions and 408 deletions
@@ -769,7 +769,7 @@ class Fp8MoEMethod(FusedMoEMethodBase):
del layer.w13_input_scale
del layer.w2_input_scale
def select_gemm_impl(self, prepare_finalize):
def select_gemm_impl(self, prepare_finalize, moe):
from vllm.model_executor.layers.fused_moe.batched_triton_or_deep_gemm_moe import ( # noqa: E501
BatchedTritonOrDeepGemmExperts)