diff --git a/aten/src/ATen/Dispatch.h b/aten/src/ATen/Dispatch.h
index f3be592..614a4e8 100644
--- a/aten/src/ATen/Dispatch.h
+++ b/aten/src/ATen/Dispatch.h
@@ -398,29 +398,6 @@
       AT_PRIVATE_CASE_TYPE(at::ScalarType::Long, int64_t, __VA_ARGS__)      \
       AT_PRIVATE_CASE_TYPE(at::ScalarType::Short, int16_t, __VA_ARGS__)     \
       AT_PRIVATE_CASE_TYPE(                                                 \
-          at::ScalarType::ComplexFloat, std::complex<float>, __VA_ARGS__)   \
-      AT_PRIVATE_CASE_TYPE(                                                 \
-          at::ScalarType::ComplexDouble, std::complex<double>, __VA_ARGS__) \
-      AT_PRIVATE_CASE_TYPE(                                                 \
-          SCALARTYPE,                                                       \
-          decltype(c10::impl::ScalarTypeToCPPType<SCALARTYPE>::t),          \
-          __VA_ARGS__)                                                      \
-      default:                                                              \
-        AT_ERROR(#NAME, " not implemented for '", toString(TYPE), "'");     \
-    }                                                                       \
-  }()
-
-#define AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(SCALARTYPE, TYPE, NAME, ...)  \
-  [&] {                                                                     \
-    switch (TYPE) {                                                         \
-      AT_PRIVATE_CASE_TYPE(at::ScalarType::Byte, uint8_t, __VA_ARGS__)      \
-      AT_PRIVATE_CASE_TYPE(at::ScalarType::Char, int8_t, __VA_ARGS__)       \
-      AT_PRIVATE_CASE_TYPE(at::ScalarType::Double, double, __VA_ARGS__)     \
-      AT_PRIVATE_CASE_TYPE(at::ScalarType::Float, float, __VA_ARGS__)       \
-      AT_PRIVATE_CASE_TYPE(at::ScalarType::Int, int32_t, __VA_ARGS__)       \
-      AT_PRIVATE_CASE_TYPE(at::ScalarType::Long, int64_t, __VA_ARGS__)      \
-      AT_PRIVATE_CASE_TYPE(at::ScalarType::Short, int16_t, __VA_ARGS__)     \
-      AT_PRIVATE_CASE_TYPE(                                                 \
           at::ScalarType::ComplexFloat, c10::complex<float>, __VA_ARGS__)   \
       AT_PRIVATE_CASE_TYPE(                                                 \
           at::ScalarType::ComplexDouble, c10::complex<double>, __VA_ARGS__) \
diff --git a/aten/src/ATen/native/Blas.cpp b/aten/src/ATen/native/Blas.cpp
index be32b8f..aa9fcbb 100644
--- a/aten/src/ATen/native/Blas.cpp
+++ b/aten/src/ATen/native/Blas.cpp
@@ -13,7 +13,7 @@
 
 Tensor &addmv_impl_cpu(Tensor& result, const Tensor &self, const Tensor &mat, const Tensor &vec, Scalar beta_, Scalar alpha_) {
   auto r_stride = result.stride(0);
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(kBFloat16, mat.scalar_type(), "addmv_impl_cpu", [&] {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(kBFloat16, mat.scalar_type(), "addmv_impl_cpu", [&] {
     auto beta = beta_.to<scalar_t>();
     auto alpha = alpha_.to<scalar_t>();
     bool is_fast = false;
diff --git a/aten/src/ATen/native/cpu/FillKernel.cpp b/aten/src/ATen/native/cpu/FillKernel.cpp
index 0237a57..22e7f72 100644
--- a/aten/src/ATen/native/cpu/FillKernel.cpp
+++ b/aten/src/ATen/native/cpu/FillKernel.cpp
@@ -29,7 +29,7 @@
   } else if (iter.dtype() == ScalarType::BFloat16) {
     fill_non_native_type<at::BFloat16>(iter, value_scalar);
   } else {
-    AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(at::ScalarType::Bool, iter.dtype(), "fill_cpu", [&]() {
+    AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(at::ScalarType::Bool, iter.dtype(), "fill_cpu", [&]() {
       scalar_t value = value_scalar.to<scalar_t>();
       cpu_kernel_vec(
           iter,
diff --git a/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp b/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp
index 61ff791..a9d54a3 100644
--- a/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp
+++ b/aten/src/ATen/native/cpu/ReduceOpsKernel.cpp
@@ -267,7 +267,7 @@
 }
 
 static void min_values_kernel_impl(TensorIterator& iter) {
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(kHalf, iter.dtype(), "min_values_cpu", [&iter] {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(kHalf, iter.dtype(), "min_values_cpu", [&iter] {
     binary_kernel_reduce_vec(
       iter,
       [](scalar_t a, scalar_t b) -> scalar_t { return min_impl(a, b); },
@@ -276,7 +276,7 @@
 }
 
 static void max_values_kernel_impl(TensorIterator& iter) {
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(kHalf, iter.dtype(), "max_values_cpu", [&iter] {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(kHalf, iter.dtype(), "max_values_cpu", [&iter] {
     binary_kernel_reduce_vec(
       iter,
       [](scalar_t a, scalar_t b) -> scalar_t { return max_impl(a, b); },
diff --git a/aten/src/ATen/native/cpu/TensorCompareKernel.cpp b/aten/src/ATen/native/cpu/TensorCompareKernel.cpp
index b22580b..aaca181 100644
--- a/aten/src/ATen/native/cpu/TensorCompareKernel.cpp
+++ b/aten/src/ATen/native/cpu/TensorCompareKernel.cpp
@@ -83,7 +83,7 @@
   auto wrap_dim = maybe_wrap_dim(dim, self.dim());
   int64_t self_dim_size = ensure_nonempty_size(self, wrap_dim);
 
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(ScalarType::Bool, self.scalar_type(), "min_cpu", [&] {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(ScalarType::Bool, self.scalar_type(), "min_cpu", [&] {
     compare_base_kernel<scalar_t>(result, indice, self, wrap_dim, keepdim, [&] (
       scalar_t* result_data, int64_t* indice_data,
       const scalar_t* self_data, auto self_dim_stride) {
@@ -117,7 +117,7 @@
   auto wrap_dim = maybe_wrap_dim(dim, self.dim());
   int64_t self_dim_size = ensure_nonempty_size(self, wrap_dim);
 
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(ScalarType::Bool, self.scalar_type(), "max_cpu", [&] {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(ScalarType::Bool, self.scalar_type(), "max_cpu", [&] {
     compare_base_kernel<scalar_t>(result, indice, self, wrap_dim, keepdim, [&] (
       scalar_t* result_data, int64_t* indice_data,
       const scalar_t* self_data, auto self_dim_stride) {
diff --git a/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp b/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp
index d39302a..825da23 100644
--- a/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp
+++ b/aten/src/ATen/native/cpu/UnaryOpsKernel.cpp
@@ -222,7 +222,7 @@
 }
 
 static void clamp_kernel(TensorIterator& iter, Scalar min_scalar, Scalar max_scalar) {
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(kBFloat16, iter.dtype(), "clamp_cpu", [&]() {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(kBFloat16, iter.dtype(), "clamp_cpu", [&]() {
     c10::scalar_value_type<scalar_t>::type (*zabs_)(scalar_t) = zabs;
     auto min = min_scalar.to<scalar_t>();
     auto max = max_scalar.to<scalar_t>();
@@ -235,7 +235,7 @@
 }
 
 static void clamp_max_kernel(TensorIterator& iter, Scalar max_scalar) {
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(kBFloat16, iter.dtype(), "clamp_max_cpu", [&]() {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(kBFloat16, iter.dtype(), "clamp_max_cpu", [&]() {
     c10::scalar_value_type<scalar_t>::type (*zabs_)(scalar_t) = zabs;
     auto max = max_scalar.to<scalar_t>();
     auto max_vec = Vec256<scalar_t>(max);
@@ -246,7 +246,7 @@
 }
 
 static void clamp_min_kernel(TensorIterator& iter, Scalar min_scalar) {
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(kBFloat16, iter.dtype(), "clamp_min_cpu", [&]() {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(kBFloat16, iter.dtype(), "clamp_min_cpu", [&]() {
     c10::scalar_value_type<scalar_t>::type (*zabs_)(scalar_t) = zabs;
     auto min = min_scalar.to<scalar_t>();
     auto min_vec = Vec256<scalar_t>(min);
diff --git a/aten/src/ATen/native/cuda/ReduceSumProdKernel.cu b/aten/src/ATen/native/cuda/ReduceSumProdKernel.cu
index 4b28d02..6506d6d 100644
--- a/aten/src/ATen/native/cuda/ReduceSumProdKernel.cu
+++ b/aten/src/ATen/native/cuda/ReduceSumProdKernel.cu
@@ -36,7 +36,7 @@
     return sum_kernel_impl<at::BFloat16, float, float>(iter);
   }
   #endif
-  AT_DISPATCH_ALL_TYPES_AND_C10_COMPLEX_AND(ScalarType::Bool, iter.dtype(), "sum_cuda", [&]() {
+  AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND(ScalarType::Bool, iter.dtype(), "sum_cuda", [&]() {
     sum_kernel_impl<scalar_t>(iter);
   });
 }