apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

format flash_mask_attn

Browse Source
This commit is contained in:
lizhenyun01
2025-11-18 13:33:37 +08:00
parent cd2c4df64a
commit d11235333e
2 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
custom_ops/gpu_ops/flash_mask_attn/softmax.hpp
View File

@@ -188,7 +188,7 @@ struct Softmax {
using TensorT = decltype(make_tensor<float>(Shape<Int<kNRows>>{}));
TensorT row_max, row_sum;
CUTLASS_DEVICE Softmax() {};
CUTLASS_DEVICE Softmax(){};
template <bool Is_first, bool Check_inf = false, typename Tensor0>
__forceinline__ __device__ TensorT max(Tensor0 &acc_s,