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

This commit is contained in:
Yongye Zhu
2026-03-25 10:16:40 -07:00
committed by GitHub
parent bf4cc9ed2d
commit 678b3c99e8
6 changed files with 574 additions and 245 deletions
+1 -1
View File
@@ -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_moe import (
from vllm.model_executor.layers.fused_moe.experts.flashinfer_cutedsl_batched_moe import ( # noqa: E501
flashinfer_cutedsl_moe_masked,
)
from vllm.utils.flashinfer import (