fbgemm_gpu/include/fbgemm_gpu/sparse_ops.h
fbgemm_gpu/src/sparse_ops_cpu.cpp

fbgemm_gpu/include/fbgemm_gpu/cpu_utils.h
fbgemm_gpu/src/cpu_utils.cpp

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/split_embeddings_utils.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/quantize_ops.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/permute_pooled_embedding_ops.cu

fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/cumem_utils.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh
fbgemm_gpu/src/split_embeddings_cache_cuda.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/jagged_tensor_ops.cu

fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh
fbgemm_gpu/src/layout_transform_ops.cu

fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh
fbgemm_gpu/src/histogram_binning_calibration_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh
fbgemm_gpu/src/sparse_ops.cu

fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh
fbgemm_gpu/src/layout_transform_ops.cu