| /aosp_15_r20/external/pytorch/aten/src/ATen/native/nested/cuda/ |
| H A D | NestedTensorMatmul.cu | 187 int64_t ntensors) { in group_gemm_dispatch()
201 int64_t ntensors) { in group_gemm_dispatch()
227 int64_t ntensors) { in group_gemm_dispatch()
292 int64_t ntensors = self_ptr->size(0), ntensors2 = mat2_ptr->size(0); in bmm_nested_cuda() local
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/nested/ |
| H A D | NestedTensorMath.cpp | 385 int64_t ntensors = nt_input->size(0); in NestedTensor_sum_dim_CPU() local
434 int64_t ntensors = self_ptr->size(0); in select_nested() local
509 int64_t ntensors = input_ptr->size(0); in softmax_nested() local
547 int64_t ntensors = input_ptr->size(0); in NestedTensor_all() local
709 int64_t ntensors = static_cast<int64_t>(sizes.size()); in NestedTensor_compute_size_stride() local
825 int64_t ntensors = self_ptr->size(0); in view_nested() local
916 int64_t ntensors = self_ptr->size(0); in reshape_nested() local
|
| H A D | NestedTensorMatmul.cpp | 24 int64_t ntensors = self.is_nested() ? get_nested_tensor_impl(self)->size(0) : self.size(0); in bmm_nested() local
250 int64_t ntensors = self_ptr->size(0), ntensors2 = mat2_ptr->size(0); in matmul_nested() local
|
| H A D | NestedTensorBackward.cpp | 84 int64_t ntensors = output_ptr->size(0); in nested_softmax_backward() local
129 int64_t ntensors = nt_self->size(0); in _nested_sum_backward_cpu() local
|
| H A D | NestedTensorUtils.h | 110 int64_t ntensors = self_ptr->size(0); in NestedTensor_get_sizes() local
143 int64_t ntensors = self_ptr->size(0); in NestedTensor_get_strides() local
|
| H A D | NestedTensorUnaryOps.cpp | 38 int64_t ntensors = condition_ptr->size(0); in NestedTensor_where() local
|
| H A D | NestedTensorFactories.cpp | 179 int64_t ntensors = self_ptr->size(0); in NestedTensor_unbind() local
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/ |
| H A D | TensorIteratorInternal.h | 28 const auto ntensors = base.size(); in get_data_ptrs() local
43 size_t ntensors, in serial_for_each()
|
| H A D | NestedTensorImpl.h | 225 int64_t ntensors = nt->size(0); in nested_tensor_impl_is_contiguous() local
|
| H A D | NestedTensorImpl.cpp | 147 int64_t ntensors = sizes.size(0), orig_dim = sizes.size(1); in construct_offsets() local
|
| H A D | TensorIterator.cpp | 54 auto ntensors = operands.size(); in get_strides() local
787 const auto ntensors = this->ntensors(); in serial_for_each() local
|
| H A D | TensorIterator.h | 280 int ntensors() const { in ntensors() function
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/cuda/ |
| H A D | CUDALoops.cuh | 254 constexpr int ntensors = traits::arity + 1; in gpu_kernel_impl_nocast() local
289 constexpr int ntensors = traits::arity + 1; in gpu_kernel_impl() local
|
| H A D | ForeachReduceOp.cu | 146 const size_t ntensors = tensors.size(); in foreach_tensor_max_cuda() local
435 const size_t ntensors = tensors.size(); in foreach_tensor_norm_cuda() local
|
| H A D | CUDAJitLoops.cuh | 189 constexpr int ntensors = arity + 1; in jitted_gpu_kernel_generic() local
|
| H A D | Loops.cuh | 280 constexpr int ntensors = num_outputs + num_inputs; in gpu_kernel_multiple_outputs_impl() local
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/cpu/ |
| H A D | IndexKernel.cpp | 466 static constexpr int ntensors = 2; in cpu_hflip_vec() local
537 static constexpr int ntensors = 2; in cpu_vflip_memcpy() local
673 static constexpr int ntensors = 2; in cpu_hflip_channels_last_vec() local
|
| H A D | Loops.h | 117 constexpr int ntensors = traits::arity + 1; in basic_loop() local
|
| /aosp_15_r20/external/pytorch/test/cpp/c10d/example/ |
| H A D | allreduce.cpp | 14 const auto ntensors = 10; in main() local
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/cuda/ |
| H A D | jiterator_impl.h | 132 int ntensors = iter.ntensors(); in ArrayVariant() local
|
| /aosp_15_r20/external/pytorch/test/ |
| H A D | test_nestedtensor.py | 1610 def test_sum(device, dtype, ntensors, max_sizes, dim, keepdim=True): argument
|