diff --git a/vllm/model_executor/kernels/linear/nvfp4/flashinfer.py b/vllm/model_executor/kernels/linear/nvfp4/flashinfer.py index 8ee0568950..bcd47fda96 100644 --- a/vllm/model_executor/kernels/linear/nvfp4/flashinfer.py +++ b/vllm/model_executor/kernels/linear/nvfp4/flashinfer.py @@ -5,6 +5,7 @@ import torch from vllm._custom_ops import scaled_fp4_quant from vllm.model_executor.layers.quantization.utils.nvfp4_utils import ( + pad_nvfp4_activation_for_cutlass, pad_nvfp4_weight_for_cutlass, slice_nvfp4_output, swizzle_blockscale,