small fix sum cuda

This commit is contained in:
lucasdelimanogueira 2024-05-22 20:59:46 -03:00
parent 950cde13f7
commit 2c7571c371

View file

@ -211,6 +211,7 @@ 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) {