diff --git a/build/cuda.cu.o b/build/cuda.cu.o index a60bfa8..94ea9cd 100644 Binary files a/build/cuda.cu.o and b/build/cuda.cu.o differ diff --git a/norch/csrc/cuda.cu b/norch/csrc/cuda.cu index 8102e7c..46af278 100644 --- a/norch/csrc/cuda.cu +++ b/norch/csrc/cuda.cu @@ -194,7 +194,7 @@ __host__ void sum_tensor_cuda(Tensor* tensor, float* result_data, int axis) { } cudaDeviceSynchronize(); - + } else { int axis_size = tensor->shape[axis]; diff --git a/norch/csrc/tensor.cpp b/norch/csrc/tensor.cpp index 1f374f8..1fc95e1 100644 --- a/norch/csrc/tensor.cpp +++ b/norch/csrc/tensor.cpp @@ -211,7 +211,6 @@ extern "C" { float* result_data; cudaMalloc((void**)&result_data, size * sizeof(float)); - cudaMemset(result_data, 0, size * sizeof(float)); sum_tensor_cuda(tensor, result_data, axis); if (keepdim) { diff --git a/norch/libtensor.so b/norch/libtensor.so index d5ff2a2..6074e46 100755 Binary files a/norch/libtensor.so and b/norch/libtensor.so differ