BSD 3-Clause License -------------------- FBGEMM-0.6.0/LICENSE Unknown or generated -------------------- FBGEMM-0.6.0/.bazelrc FBGEMM-0.6.0/.clang-tidy FBGEMM-0.6.0/.github/scripts/fbgemm_gpu_build.bash FBGEMM-0.6.0/.github/scripts/fbgemm_gpu_docs.bash FBGEMM-0.6.0/.github/scripts/fbgemm_gpu_install.bash FBGEMM-0.6.0/.github/scripts/fbgemm_gpu_lint.bash FBGEMM-0.6.0/.github/scripts/fbgemm_gpu_test.bash FBGEMM-0.6.0/.github/scripts/nova_dir.bash FBGEMM-0.6.0/.github/scripts/nova_postscript.bash FBGEMM-0.6.0/.github/scripts/nova_prescript.bash FBGEMM-0.6.0/.github/scripts/setup_env.bash FBGEMM-0.6.0/.github/scripts/test_torchrec.bash FBGEMM-0.6.0/.github/scripts/utils_base.bash FBGEMM-0.6.0/.github/scripts/utils_build.bash FBGEMM-0.6.0/.github/scripts/utils_conda.bash FBGEMM-0.6.0/.github/scripts/utils_cuda.bash FBGEMM-0.6.0/.github/scripts/utils_pip.bash FBGEMM-0.6.0/.github/scripts/utils_pytorch.bash FBGEMM-0.6.0/.github/scripts/utils_rocm.bash FBGEMM-0.6.0/.github/scripts/utils_system.bash FBGEMM-0.6.0/.github/workflows/build_wheels_linux_aarch64.yml FBGEMM-0.6.0/.github/workflows/build_wheels_linux_x86.yml FBGEMM-0.6.0/.github/workflows/fbgemm_ci.yml FBGEMM-0.6.0/.github/workflows/fbgemm_gpu_ci_cpu.yml FBGEMM-0.6.0/.github/workflows/fbgemm_gpu_ci_cuda.yml FBGEMM-0.6.0/.github/workflows/fbgemm_gpu_ci_rocm.yml FBGEMM-0.6.0/.github/workflows/fbgemm_gpu_docs.yml FBGEMM-0.6.0/.github/workflows/fbgemm_gpu_lint.yml FBGEMM-0.6.0/.github/workflows/fbgemm_gpu_pip.yml FBGEMM-0.6.0/.github/workflows/fbgemm_gpu_release_cpu.yml FBGEMM-0.6.0/.github/workflows/fbgemm_gpu_release_cuda.yml FBGEMM-0.6.0/.gitmodules FBGEMM-0.6.0/BUILD.bazel FBGEMM-0.6.0/CMakeLists.txt FBGEMM-0.6.0/CODE_OF_CONDUCT.md FBGEMM-0.6.0/CONTRIBUTING.md FBGEMM-0.6.0/README.md FBGEMM-0.6.0/WORKSPACE.bazel FBGEMM-0.6.0/bench/AlignedVec.h FBGEMM-0.6.0/bench/BenchUtils.cc FBGEMM-0.6.0/bench/BenchUtils.h FBGEMM-0.6.0/bench/CMakeLists.txt FBGEMM-0.6.0/bench/ConvUnifiedBenchmark.cc FBGEMM-0.6.0/bench/ConvertBenchmark.cc FBGEMM-0.6.0/bench/Depthwise3DBenchmark.cc FBGEMM-0.6.0/bench/DepthwiseBenchmark.cc FBGEMM-0.6.0/bench/EmbeddingIndexRemappingBenchmark.cc FBGEMM-0.6.0/bench/EmbeddingQuantizeBenchmark.cc FBGEMM-0.6.0/bench/EmbeddingSpMDM8BitBenchmark.cc FBGEMM-0.6.0/bench/EmbeddingSpMDMBenchmark.cc FBGEMM-0.6.0/bench/EmbeddingSpMDMNBitBenchmark.cc FBGEMM-0.6.0/bench/EmbeddingSpMDMNBitRowWiseSparseBenchmark.cc FBGEMM-0.6.0/bench/FP16Benchmark.cc FBGEMM-0.6.0/bench/GEMMsBenchmark.cc FBGEMM-0.6.0/bench/GEMMsTunableBenchmark.cc FBGEMM-0.6.0/bench/GroupwiseConvRequantizeBenchmark.cc FBGEMM-0.6.0/bench/I64Benchmark.cc FBGEMM-0.6.0/bench/I8SpmdmBenchmark.cc FBGEMM-0.6.0/bench/Im2ColFusedRequantizeBenchmark.cc FBGEMM-0.6.0/bench/PackedFloatInOutBenchmark.cc FBGEMM-0.6.0/bench/PackedRequantizeAcc16Benchmark.cc FBGEMM-0.6.0/bench/PackedRequantizeAcc32Benchmark.cc FBGEMM-0.6.0/bench/RequantizeBenchmark.cc FBGEMM-0.6.0/bench/RowOffsetBenchmark.cc FBGEMM-0.6.0/bench/RowwiseAdagradBenchmark.cc FBGEMM-0.6.0/bench/RowwiseAdagradFusedBenchmark.cc FBGEMM-0.6.0/bench/SparseAdagradBenchmark.cc FBGEMM-0.6.0/bench/SparseDenseMMFP32Benchmark.cc FBGEMM-0.6.0/bench/SparseDenseMMInt8Benchmark.cc FBGEMM-0.6.0/bench/TransposeBenchmark.cc FBGEMM-0.6.0/cmake/modules/FindAVX.cmake FBGEMM-0.6.0/cmake/modules/FindMKL.cmake FBGEMM-0.6.0/cmake/modules/FindSphinx.cmake FBGEMM-0.6.0/defs.bzl FBGEMM-0.6.0/docs/CMakeLists.txt FBGEMM-0.6.0/docs/Doxyfile.in FBGEMM-0.6.0/docs/conf.py FBGEMM-0.6.0/docs/index.rst FBGEMM-0.6.0/docs/requirements.txt FBGEMM-0.6.0/fbgemm_gpu/CMakeLists.txt FBGEMM-0.6.0/fbgemm_gpu/README.md FBGEMM-0.6.0/fbgemm_gpu/bench/README.md FBGEMM-0.6.0/fbgemm_gpu/bench/batched_unary_embeddings_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/bench_utils.py FBGEMM-0.6.0/fbgemm_gpu/bench/histogram_binning_calibration_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/jagged_tensor_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/merge_embeddings_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/quantize_ops_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/run_tbe_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/scripts/README.md FBGEMM-0.6.0/fbgemm_gpu/bench/scripts/batch_benchmark_run.py FBGEMM-0.6.0/fbgemm_gpu/bench/sparse_ops_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/split_embeddings_cache_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/split_table_batched_embeddings_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/ssd_table_batched_embeddings_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/stride_gemm_benchmark.py FBGEMM-0.6.0/fbgemm_gpu/bench/verify_fp16_stochastic_benchmark.cu FBGEMM-0.6.0/fbgemm_gpu/cmake/Hip.cmake FBGEMM-0.6.0/fbgemm_gpu/codegen/__init__.template FBGEMM-0.6.0/fbgemm_gpu/codegen/batch_index_select_dim0_cpu_host.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/batch_index_select_dim0_host.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_code_generator.py FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_dense_host.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_dense_host_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_cpu_approx_template.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_cpu_template.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_grad_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_host_cpu_template.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_host_template.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_indice_weights_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_kernel_cta_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_kernel_warp_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_backward_split_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_bounds_check.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_bounds_check_host.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_bounds_check_host_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_common_code_generator.py FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_quantized_cpu_template.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_quantized_host.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_quantized_host_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_quantized_split_lookup.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_quantized_split_nbit_host_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_quantized_split_nbit_kernel_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_split_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_split_cpu.h FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_split_kernel_nobag_small_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_split_kernel_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_split_kernel_v2_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_split_meta_template.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_split_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_forward_template_helpers.cuh FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_op_registration.h FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_ops_placeholder.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_optimizer_code_generator.py FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_optimizer_split_device_kernel_template.cuh FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_optimizer_split_host_template.cpp FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_optimizer_split_kernel_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/embedding_optimizer_split_template.cu FBGEMM-0.6.0/fbgemm_gpu/codegen/lookup_args.py FBGEMM-0.6.0/fbgemm_gpu/codegen/optimizer_args.py FBGEMM-0.6.0/fbgemm_gpu/codegen/split_embedding_codegen_lookup_invoker.template FBGEMM-0.6.0/fbgemm_gpu/codegen/split_embedding_optimizer_codegen.template FBGEMM-0.6.0/fbgemm_gpu/docs/BuildInstructions.md FBGEMM-0.6.0/fbgemm_gpu/docs/Doxyfile.in FBGEMM-0.6.0/fbgemm_gpu/docs/InstallationInstructions.md FBGEMM-0.6.0/fbgemm_gpu/docs/Makefile FBGEMM-0.6.0/fbgemm_gpu/docs/README.md FBGEMM-0.6.0/fbgemm_gpu/docs/TestInstructions.md FBGEMM-0.6.0/fbgemm_gpu/docs/assets/example-output.png FBGEMM-0.6.0/fbgemm_gpu/docs/requirements.txt FBGEMM-0.6.0/fbgemm_gpu/docs/source/conf.py FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/cumem_utils.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/embedding_ops.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/input_combine.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/jagged_tensor_ops.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/layout_transform_ops.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/merge_pooled_embeddings.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/quantize_ops.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/sparse_ops.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/cpp-api/split_table_batched_embeddings.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/index.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/python-api/jagged_tensor_ops.rst FBGEMM-0.6.0/fbgemm_gpu/docs/source/python-api/table_batched_embedding_ops.rst FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/__init__.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/_fbgemm_gpu_docs.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/batched_unary_embeddings_ops.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/docs/__init__.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/enums.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/metrics.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/permute_pooled_embedding_modules.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/permute_pooled_embedding_modules_split.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/quantize_comm.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/quantize_utils.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/sparse_ops.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/split_embedding_configs.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/split_embedding_inference_converter.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/split_embedding_optimizer_ops.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/split_embedding_utils.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/split_table_batched_embeddings_ops.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/split_table_batched_embeddings_ops_common.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/split_table_batched_embeddings_ops_inference.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/split_table_batched_embeddings_ops_training.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/ssd_split_table_batched_embeddings_ops.py FBGEMM-0.6.0/fbgemm_gpu/fbgemm_gpu/uvm.py FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/bench_utils.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/cpu_utils.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/cub_namespace_postfix.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/cub_namespace_prefix.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/cuda_utils.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/cumem_utils.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/dispatch_macros.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/embedding_backward_template_helpers.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/embedding_common.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/embedding_inplace_update.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/enum_utils.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/fbgemm_cuda_utils.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/fbgemm_tensor_accessor.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/input_combine.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/layout_transform_ops.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/merge_pooled_embeddings.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/ops_utils.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/permute_pooled_embedding_ops.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/permute_pooled_embedding_ops_split.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/permute_pooled_embs_function.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/permute_pooled_embs_function_split.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/quantize_ops.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/quantize_ops_utils.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/sparse_ops.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/sparse_ops.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/sparse_ops_utils.h FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/split_embeddings_cache_cuda.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/split_embeddings_utils.cuh FBGEMM-0.6.0/fbgemm_gpu/include/fbgemm_gpu/topology_utils.h FBGEMM-0.6.0/fbgemm_gpu/requirements.txt FBGEMM-0.6.0/fbgemm_gpu/setup.py FBGEMM-0.6.0/fbgemm_gpu/src/embedding_inplace_ops/embedding_inplace_update.cu FBGEMM-0.6.0/fbgemm_gpu/src/embedding_inplace_ops/embedding_inplace_update_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/embedding_inplace_ops/embedding_inplace_update_gpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/embedding_inplace_ops/embedding_inplace_update_test.cpp FBGEMM-0.6.0/fbgemm_gpu/src/histogram_binning_calibration_ops.cu FBGEMM-0.6.0/fbgemm_gpu/src/input_combine_ops/input_combine.cu FBGEMM-0.6.0/fbgemm_gpu/src/input_combine_ops/input_combine_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/input_combine_ops/input_combine_gpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/batched_dense_vec_jagged_2d_mul_backward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/batched_dense_vec_jagged_2d_mul_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/common.cuh FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/dense_to_jagged_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_dense_bmm_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_dense_dense_elementwise_add_jagged_output_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_dense_elementwise_mul_backward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_dense_elementwise_mul_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_index_add_2d_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_index_select_2d_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_jagged_bmm_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_softmax_backward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_softmax_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_tensor_ops.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_tensor_ops_autograd.cpp FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_tensor_ops_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_tensor_ops_meta.cpp FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_to_padded_dense_backward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_to_padded_dense_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/jagged_unique_indices.cu FBGEMM-0.6.0/fbgemm_gpu/src/jagged_tensor_ops/keyed_jagged_index_select_dim1.cu FBGEMM-0.6.0/fbgemm_gpu/src/layout_transform_ops/layout_transform_ops.cu FBGEMM-0.6.0/fbgemm_gpu/src/layout_transform_ops/layout_transform_ops_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/layout_transform_ops/layout_transform_ops_gpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/memory_utils/common.cuh FBGEMM-0.6.0/fbgemm_gpu/src/memory_utils/common.h FBGEMM-0.6.0/fbgemm_gpu/src/memory_utils/memory_utils.cpp FBGEMM-0.6.0/fbgemm_gpu/src/memory_utils/memory_utils.cu FBGEMM-0.6.0/fbgemm_gpu/src/memory_utils/memory_utils_ops.cpp FBGEMM-0.6.0/fbgemm_gpu/src/memory_utils/memory_utils_ops.cu FBGEMM-0.6.0/fbgemm_gpu/src/merge_pooled_embedding_ops/merge_pooled_embedding_ops_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/merge_pooled_embedding_ops/merge_pooled_embedding_ops_gpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/metric_ops/metric_ops.cu FBGEMM-0.6.0/fbgemm_gpu/src/metric_ops/metric_ops.h FBGEMM-0.6.0/fbgemm_gpu/src/metric_ops/metric_ops_host.cpp FBGEMM-0.6.0/fbgemm_gpu/src/permute_pooled_embedding_ops/permute_pooled_embedding_function.cpp FBGEMM-0.6.0/fbgemm_gpu/src/permute_pooled_embedding_ops/permute_pooled_embedding_ops.cu FBGEMM-0.6.0/fbgemm_gpu/src/permute_pooled_embedding_ops/permute_pooled_embedding_ops_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/permute_pooled_embedding_ops/permute_pooled_embedding_ops_gpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/permute_pooled_embedding_ops/permute_pooled_embedding_ops_split.cu FBGEMM-0.6.0/fbgemm_gpu/src/permute_pooled_embedding_ops/permute_pooled_embedding_ops_split_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/permute_pooled_embedding_ops/permute_pooled_embedding_ops_split_gpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/common.cuh FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_bfloat16.cu FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_fp8_rowwise.cu FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_fused_8bit_rowwise.cu FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_fused_nbit_rowwise.cu FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_hfp8.cu FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_msfp.cu FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_ops_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_ops_gpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_ops_meta.cpp FBGEMM-0.6.0/fbgemm_gpu/src/quantize_ops/quantize_padded_fp8_rowwise.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/common.cuh FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_async_cumsum.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_batched_unary_embeddings.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_block_bucketize_features.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_bucketize_features.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_compute_frequency_sequence.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_expand_into_jagged_permute.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_group_index.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_index_add.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_index_select.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_invert_permute.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_ops_cpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_ops_gpu.cpp FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_ops_meta.cpp FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_pack_segments_backward.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_pack_segments_forward.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_permute102.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_permute_1d.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_permute_2d.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_permute_embeddings.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_range.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_reorder_batched_ad.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_segment_sum_csr.cu FBGEMM-0.6.0/fbgemm_gpu/src/sparse_ops/sparse_zipf.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/common.cuh FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/common.h FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lfu_cache_find.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lfu_cache_populate.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lfu_cache_populate_byte.cpp FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lfu_cache_populate_byte.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/linearize_cache_indices.cpp FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/linearize_cache_indices.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lru_cache_find.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lru_cache_populate.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lru_cache_populate_byte.cpp FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lru_cache_populate_byte.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lxu_cache.cpp FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/lxu_cache.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/reset_weight_momentum.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/split_embeddings_cache_ops.cpp FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_cache/split_embeddings_cache_ops.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_utils/generate_vbe_metadata.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_utils/get_infos_metadata.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_utils/radix_sort_pairs.cu FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_utils/split_embeddings_utils.cpp FBGEMM-0.6.0/fbgemm_gpu/src/split_embeddings_utils/transpose_embedding_input.cu FBGEMM-0.6.0/fbgemm_gpu/src/ssd_split_embeddings_cache/ssd_split_embeddings_cache_cuda.cu FBGEMM-0.6.0/fbgemm_gpu/src/ssd_split_embeddings_cache/ssd_split_table_batched_embeddings.cpp FBGEMM-0.6.0/fbgemm_gpu/src/ssd_split_embeddings_cache/ssd_table_batched_embeddings.h FBGEMM-0.6.0/fbgemm_gpu/src/topology_utils.cpp FBGEMM-0.6.0/fbgemm_gpu/test/batched_unary_embeddings_test.py FBGEMM-0.6.0/fbgemm_gpu/test/cpu_kernel_test.cpp FBGEMM-0.6.0/fbgemm_gpu/test/failures_dict.json FBGEMM-0.6.0/fbgemm_gpu/test/failures_dict_fast.json FBGEMM-0.6.0/fbgemm_gpu/test/input_combine_test.py FBGEMM-0.6.0/fbgemm_gpu/test/jagged_tensor_ops_test.py FBGEMM-0.6.0/fbgemm_gpu/test/layout_transform_ops_test.py FBGEMM-0.6.0/fbgemm_gpu/test/lint/check_meta_header.py FBGEMM-0.6.0/fbgemm_gpu/test/lint/flake8_problem_matcher.json FBGEMM-0.6.0/fbgemm_gpu/test/merge_pooled_embeddings_test.py FBGEMM-0.6.0/fbgemm_gpu/test/metric_ops_test.py FBGEMM-0.6.0/fbgemm_gpu/test/permute_pooled_embedding_split_test.py FBGEMM-0.6.0/fbgemm_gpu/test/permute_pooled_embedding_test.py FBGEMM-0.6.0/fbgemm_gpu/test/quantize_comm_test.py FBGEMM-0.6.0/fbgemm_gpu/test/quantize_ops_test.py FBGEMM-0.6.0/fbgemm_gpu/test/sparse_ops_test.py FBGEMM-0.6.0/fbgemm_gpu/test/sparse_ops_utils_test.cpp FBGEMM-0.6.0/fbgemm_gpu/test/split_embedding_inference_converter_test.py FBGEMM-0.6.0/fbgemm_gpu/test/split_embeddings_utils_test.py FBGEMM-0.6.0/fbgemm_gpu/test/split_table_batched_embeddings_test.py FBGEMM-0.6.0/fbgemm_gpu/test/ssd_split_table_batched_embeddings_test.py FBGEMM-0.6.0/fbgemm_gpu/test/tensor_assert_test.cpp FBGEMM-0.6.0/fbgemm_gpu/test/test_utils.py FBGEMM-0.6.0/fbgemm_gpu/test/uvm_cache_miss_emulate_test.cpp FBGEMM-0.6.0/fbgemm_gpu/test/uvm_test.py FBGEMM-0.6.0/include/fbgemm/ConvUtils.h FBGEMM-0.6.0/include/fbgemm/Fbgemm.h FBGEMM-0.6.0/include/fbgemm/FbgemmBuild.h FBGEMM-0.6.0/include/fbgemm/FbgemmConvert.h FBGEMM-0.6.0/include/fbgemm/FbgemmEmbedding.h FBGEMM-0.6.0/include/fbgemm/FbgemmFP16.h FBGEMM-0.6.0/include/fbgemm/FbgemmFPCommon.h FBGEMM-0.6.0/include/fbgemm/FbgemmI64.h FBGEMM-0.6.0/include/fbgemm/FbgemmI8DepthwiseAvx2.h FBGEMM-0.6.0/include/fbgemm/FbgemmI8DirectconvAvx2.h FBGEMM-0.6.0/include/fbgemm/FbgemmI8Spmdm.h FBGEMM-0.6.0/include/fbgemm/FbgemmPackMatrixB.h FBGEMM-0.6.0/include/fbgemm/FbgemmSparse.h FBGEMM-0.6.0/include/fbgemm/OutputProcessing-inl.h FBGEMM-0.6.0/include/fbgemm/PackingTraits-inl.h FBGEMM-0.6.0/include/fbgemm/QuantUtils.h FBGEMM-0.6.0/include/fbgemm/QuantUtilsAvx2.h FBGEMM-0.6.0/include/fbgemm/QuantUtilsAvx512.h FBGEMM-0.6.0/include/fbgemm/SimdUtils.h FBGEMM-0.6.0/include/fbgemm/Types.h FBGEMM-0.6.0/include/fbgemm/Utils.h FBGEMM-0.6.0/include/fbgemm/UtilsAvx2.h FBGEMM-0.6.0/include/fbgemm/spmmUtils.h FBGEMM-0.6.0/include/fbgemm/spmmUtilsAvx2.h FBGEMM-0.6.0/netlify.toml FBGEMM-0.6.0/src/CodeCache.h FBGEMM-0.6.0/src/CodeGenHelpers.h FBGEMM-0.6.0/src/DirectConv.h FBGEMM-0.6.0/src/EmbeddingSpMDM.cc FBGEMM-0.6.0/src/EmbeddingSpMDMAvx2.cc FBGEMM-0.6.0/src/EmbeddingSpMDMAvx512.cc FBGEMM-0.6.0/src/EmbeddingSpMDMNBit.cc FBGEMM-0.6.0/src/ExecuteKernel.cc FBGEMM-0.6.0/src/ExecuteKernel.h FBGEMM-0.6.0/src/ExecuteKernelGeneric.h FBGEMM-0.6.0/src/ExecuteKernelU8S8.cc FBGEMM-0.6.0/src/ExecuteKernelU8S8.h FBGEMM-0.6.0/src/Fbgemm.cc FBGEMM-0.6.0/src/FbgemmBfloat16Convert.cc FBGEMM-0.6.0/src/FbgemmBfloat16ConvertAvx2.cc FBGEMM-0.6.0/src/FbgemmBfloat16ConvertAvx512.cc FBGEMM-0.6.0/src/FbgemmConv.cc FBGEMM-0.6.0/src/FbgemmFP16.cc FBGEMM-0.6.0/src/FbgemmFP16UKernelsAvx2.cc FBGEMM-0.6.0/src/FbgemmFP16UKernelsAvx2.h FBGEMM-0.6.0/src/FbgemmFP16UKernelsAvx512.cc FBGEMM-0.6.0/src/FbgemmFP16UKernelsAvx512.h FBGEMM-0.6.0/src/FbgemmFP16UKernelsAvx512_256.cc FBGEMM-0.6.0/src/FbgemmFP16UKernelsAvx512_256.h FBGEMM-0.6.0/src/FbgemmFP16UKernelsIntrinsicAvx2.cc FBGEMM-0.6.0/src/FbgemmFP16UKernelsIntrinsicAvx512.cc FBGEMM-0.6.0/src/FbgemmFP16UKernelsIntrinsicAvx512_256.cc FBGEMM-0.6.0/src/FbgemmFPCommon.cc FBGEMM-0.6.0/src/FbgemmFloat16Convert.cc FBGEMM-0.6.0/src/FbgemmFloat16ConvertAvx2.cc FBGEMM-0.6.0/src/FbgemmFloat16ConvertAvx512.cc FBGEMM-0.6.0/src/FbgemmI64.cc FBGEMM-0.6.0/src/FbgemmI8Depthwise2DAvx2-inl.h FBGEMM-0.6.0/src/FbgemmI8Depthwise3DAvx2.cc FBGEMM-0.6.0/src/FbgemmI8DepthwiseAvx2-inl.h FBGEMM-0.6.0/src/FbgemmI8DepthwiseAvx2.cc FBGEMM-0.6.0/src/FbgemmI8DepthwisePerChannelQuantAvx2.cc FBGEMM-0.6.0/src/FbgemmI8Spmdm.cc FBGEMM-0.6.0/src/FbgemmSparseDense.cc FBGEMM-0.6.0/src/FbgemmSparseDenseAvx2.cc FBGEMM-0.6.0/src/FbgemmSparseDenseAvx512.cc FBGEMM-0.6.0/src/FbgemmSparseDenseInt8Avx2.cc FBGEMM-0.6.0/src/FbgemmSparseDenseInt8Avx512.cc FBGEMM-0.6.0/src/FbgemmSparseDenseVectorInt8Avx512.cc FBGEMM-0.6.0/src/GenerateI8Depthwise.cc FBGEMM-0.6.0/src/GenerateI8Depthwise.h FBGEMM-0.6.0/src/GenerateKernel.cc FBGEMM-0.6.0/src/GenerateKernel.h FBGEMM-0.6.0/src/GenerateKernelDirectConvU8S8S32ACC32.cc FBGEMM-0.6.0/src/GenerateKernelU8S8S32ACC16.cc FBGEMM-0.6.0/src/GenerateKernelU8S8S32ACC16Avx512.cc FBGEMM-0.6.0/src/GenerateKernelU8S8S32ACC16Avx512VNNI.cc FBGEMM-0.6.0/src/GenerateKernelU8S8S32ACC32.cc FBGEMM-0.6.0/src/GenerateKernelU8S8S32ACC32Avx512VNNI.cc FBGEMM-0.6.0/src/GroupwiseConv.cc FBGEMM-0.6.0/src/GroupwiseConv.h FBGEMM-0.6.0/src/GroupwiseConvAcc32Avx2.cc FBGEMM-0.6.0/src/GroupwiseConvAcc32Avx512.cc FBGEMM-0.6.0/src/InlineAsmDefines.h FBGEMM-0.6.0/src/MaskAvx2.h FBGEMM-0.6.0/src/OptimizedKernelsAvx2.cc FBGEMM-0.6.0/src/OptimizedKernelsAvx2.h FBGEMM-0.6.0/src/PackAMatrix.cc FBGEMM-0.6.0/src/PackAWithIm2Col.cc FBGEMM-0.6.0/src/PackAWithQuantRowOffset.cc FBGEMM-0.6.0/src/PackAWithRowOffset.cc FBGEMM-0.6.0/src/PackBMatrix.cc FBGEMM-0.6.0/src/PackDepthwiseConvMatrixAvx2.cc FBGEMM-0.6.0/src/PackMatrix.cc FBGEMM-0.6.0/src/PackWeightMatrixForGConv.cc FBGEMM-0.6.0/src/PackWeightsForConv.cc FBGEMM-0.6.0/src/PackWeightsForDirectConv.cc FBGEMM-0.6.0/src/QuantUtils.cc FBGEMM-0.6.0/src/QuantUtilsAvx2.cc FBGEMM-0.6.0/src/QuantUtilsAvx512.cc FBGEMM-0.6.0/src/RefImplementations.cc FBGEMM-0.6.0/src/RefImplementations.h FBGEMM-0.6.0/src/RowWiseSparseAdagradFused.cc FBGEMM-0.6.0/src/SparseAdagrad.cc FBGEMM-0.6.0/src/TransposeUtils.cc FBGEMM-0.6.0/src/TransposeUtils.h FBGEMM-0.6.0/src/TransposeUtilsAvx2.h FBGEMM-0.6.0/src/Utils.cc FBGEMM-0.6.0/src/UtilsAvx2.cc FBGEMM-0.6.0/src/UtilsAvx512.cc FBGEMM-0.6.0/src/codegen_fp16fp32.cc FBGEMM-0.6.0/src/spmmUtils.cc FBGEMM-0.6.0/src/spmmUtilsAvx2.cc FBGEMM-0.6.0/test/Bfloat16ConvertTest.cc FBGEMM-0.6.0/test/CMakeLists.txt FBGEMM-0.6.0/test/EmbeddingSpMDM8BitTest.cc FBGEMM-0.6.0/test/EmbeddingSpMDMNBitTest.cc FBGEMM-0.6.0/test/EmbeddingSpMDMTest.cc FBGEMM-0.6.0/test/EmbeddingSpMDMTestUtils.cc FBGEMM-0.6.0/test/EmbeddingSpMDMTestUtils.h FBGEMM-0.6.0/test/FBGemmFPTest.h FBGEMM-0.6.0/test/FP16Test.cc FBGEMM-0.6.0/test/Float16ConvertTest.cc FBGEMM-0.6.0/test/GConvTest.cc FBGEMM-0.6.0/test/I64Test.cc FBGEMM-0.6.0/test/I8DepthwiseTest.cc FBGEMM-0.6.0/test/I8DirectconvTest.cc FBGEMM-0.6.0/test/I8SpmdmTest.cc FBGEMM-0.6.0/test/Im2ColFusedRequantizeTest.cc FBGEMM-0.6.0/test/PackedRequantizeAcc16Test.cc FBGEMM-0.6.0/test/PackedRequantizeTest.cc FBGEMM-0.6.0/test/QuantUtilsTest.cc FBGEMM-0.6.0/test/QuantizationHelpers.cc FBGEMM-0.6.0/test/QuantizationHelpers.h FBGEMM-0.6.0/test/RadixSortTest.cc FBGEMM-0.6.0/test/RequantizeOnlyTest.cc FBGEMM-0.6.0/test/RowWiseSparseAdagradFusedTest.cc FBGEMM-0.6.0/test/SparseAdagradTest.cc FBGEMM-0.6.0/test/SparseDenseMMFP32Test.cc FBGEMM-0.6.0/test/SparseDenseMMInt8Test.cc FBGEMM-0.6.0/test/SparsePackUnpackTest.cc FBGEMM-0.6.0/test/TestUtils.cc FBGEMM-0.6.0/test/TestUtils.h FBGEMM-0.6.0/test/TransposeTest.cc FBGEMM-0.6.0/test/TransposedRequantizeTest.cc FBGEMM-0.6.0/test/UniConvTest.cc