Revert "[MoE Kernel] Flashinfer nvfp4 cutedsl moe kernel integration" (#38050) (#38169)

Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
2026-03-26 07:59:09 -07:00
parent 2e225f7bd2
commit be1a85b7a2
6 changed files with 245 additions and 574 deletions
--- a/tests/kernels/moe/test_cutedsl_moe.py
+++ b/tests/kernels/moe/test_cutedsl_moe.py
@@ -17,7 +17,7 @@ from flashinfer import fp4_quantize
 from torch.nn import functional as F

 from vllm.model_executor.layers.activation import SiluAndMul
-from vllm.model_executor.layers.fused_moe.experts.flashinfer_cutedsl_batched_moe import (  # noqa: E501
+from vllm.model_executor.layers.fused_moe.experts.flashinfer_cutedsl_moe import (
    flashinfer_cutedsl_moe_masked,
 )
 from vllm.utils.flashinfer import (