cleanup

Signed-off-by: Mayank Mishra <[email protected]>
mayank31398 · Jan 21, 2025 · 18b0cf2 · 18b0cf2
1 parent 93909d5
commit 18b0cf2
Show file tree

Hide file tree

Showing 5 changed files with 10 additions and 0 deletions.
diff --git a/cute_kernels/kernels/add/add_scalar/cuda_implementation/ops.cpp b/cute_kernels/kernels/add/add_scalar/cuda_implementation/ops.cpp
@@ -1,5 +1,7 @@
 #include <torch/extension.h>
 
+#include "../../../../include/dtypes/alias.h"
+
 void add_scalar_cuda(const torch::Tensor &x, const fp32 &y, torch::Tensor &output, const uint32 &BLOCK_SIZE);
 
 PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) { m.def("add_scalar_cuda", &add_scalar_cuda, "Scalar addition (CUDA)"); }
diff --git a/cute_kernels/kernels/add/add_tensor/cuda_implementation/ops.cpp b/cute_kernels/kernels/add/add_tensor/cuda_implementation/ops.cpp
@@ -1,5 +1,7 @@
 #include <torch/extension.h>
 
+#include "../../../../include/dtypes/alias.h"
+
 void add_tensor_cuda(const torch::Tensor &x, const torch::Tensor &y, torch::Tensor &output, const uint32 &BLOCK_SIZE);
 
 PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) { m.def("add_tensor_cuda", &add_tensor_cuda, "Tensor addition (CUDA)"); }
diff --git a/cute_kernels/kernels/continuous_count/cuda_implementation/ops.cpp b/cute_kernels/kernels/continuous_count/cuda_implementation/ops.cpp
@@ -1,5 +1,7 @@
 #include <torch/extension.h>
 
+#include "../../../include/dtypes/alias.h"
+
 void continuous_count_cuda(const torch::Tensor &x,
                            torch::Tensor &output,
                            const uint32 &sm_count,

diff --git a/cute_kernels/kernels/continuous_count_and_sort/cuda_implementation/ops.cpp b/cute_kernels/kernels/continuous_count_and_sort/cuda_implementation/ops.cpp
@@ -1,5 +1,7 @@
 #include <torch/extension.h>
 
+#include "../../../include/dtypes/alias.h"
+
 void continuous_count_and_sort_cuda(const torch::Tensor &x,
                                     torch::Tensor &count_output,
                                     torch::Tensor &sorted_output,

diff --git a/cute_kernels/kernels/swiglu/cuda_implementation/ops.cpp b/cute_kernels/kernels/swiglu/cuda_implementation/ops.cpp
@@ -1,5 +1,7 @@
 #include <torch/extension.h>
 
+#include "../../../include/dtypes/alias.h"
+
 void swiglu_forward_cuda(const torch::Tensor &gate,
                          const torch::Tensor &up,
                          torch::Tensor &output,