A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 3, 05:30 UTC
[Bugfix][CI] Add missing import of pad_nvfp4_activation_for_cutlass in flashinfer (#43237)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Flora Feng committed
May 20, 2026 at 14:59 UTC
2a43b407c5093b1255a172139da6a5151f410b7a
1 file changed
+1
vllm/model_executor/kernels/linear/nvfp4/flashinfer.py
+1
@@ -5,6 +5,7 @@ import torch
5
6
from vllm._custom_ops import scaled_fp4_quant
7
from vllm.model_executor.layers.quantization.utils.nvfp4_utils import (
8
+ pad_nvfp4_activation_for_cutlass,
9
pad_nvfp4_weight_for_cutlass,
10
slice_nvfp4_output,
11
swizzle_blockscale,