Directory listing for /vllm/build/temp.linux-x86_64-cpython-310/.deps/cutlass-src/examples/

• 00_basic_gemm/
• 01_cutlass_utilities/
• 02_dump_reg_shmem/
• 03_visualize_layout/
• 04_tile_iterator/
• 05_batched_gemm/
• 06_splitK_gemm/
• 07_volta_tensorop_gemm/
• 08_turing_tensorop_gemm/
• 09_turing_tensorop_conv2dfprop/
• 10_planar_complex/
• 11_planar_complex_array/
• 12_gemm_bias_relu/
• 13_two_tensor_op_fusion/
• 14_ampere_tf32_tensorop_gemm/
• 15_ampere_sparse_tensorop_gemm/
• 16_ampere_tensorop_conv2dfprop/
• 17_fprop_per_channel_bias/
• 18_ampere_fp64_tensorop_affine2_gemm/
• 19_tensorop_canonical/
• 20_simt_canonical/
• 21_quaternion_gemm/
• 22_quaternion_conv/
• 23_ampere_gemm_operand_reduction_fusion/
• 24_gemm_grouped/
• 25_ampere_fprop_mainloop_fusion/
• 26_ampere_wgrad_mainloop_fusion/
• 27_ampere_3xtf32_fast_accurate_tensorop_gemm/
• 28_ampere_3xtf32_fast_accurate_tensorop_fprop/
• 29_ampere_3xtf32_fast_accurate_tensorop_complex_gemm/
• 30_wgrad_split_k/
• 31_basic_syrk/
• 32_basic_trmm/
• 33_ampere_3xtf32_tensorop_symm/
• 34_transposed_conv2d/
• 35_gemm_softmax/
• 36_gather_scatter_fusion/
• 37_gemm_layernorm_gemm_fusion/
• 38_syr2k_grouped/
• 39_gemm_permute/
• 40_cutlass_py/
• 41_fused_multi_head_attention/
• 42_ampere_tensorop_group_conv/
• 43_ell_block_sparse_gemm/
• 44_multi_gemm_ir_and_codegen/
• 45_dual_gemm/
• 46_depthwise_simt_conv2dfprop/
• 47_ampere_gemm_universal_streamk/
• 48_hopper_warp_specialized_gemm/
• 49_hopper_gemm_with_collective_builder/
• 50_hopper_gemm_with_epilogue_swizzle/
• 51_hopper_gett/
• 52_hopper_gather_scatter_fusion/
• 53_hopper_gemm_permute/
• 54_hopper_fp8_warp_specialized_gemm/
• 55_hopper_mixed_dtype_gemm/
• 56_hopper_ptr_array_batched_gemm/
• 57_hopper_grouped_gemm/
• 58_ada_fp8_gemm/
• 59_ampere_gather_scatter_conv/
• 60_cutlass_import/
• 61_hopper_gemm_with_topk_and_softmax/
• 62_hopper_sparse_gemm/
• 63_hopper_gemm_with_weight_prefetch/
• 64_ada_fp8_gemm_grouped/
• 65_distributed_gemm/
• 67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling/
• 68_hopper_fp8_warp_specialized_grouped_gemm_with_blockwise_scaling/
• 69_hopper_mixed_dtype_grouped_gemm/
• 70_blackwell_gemm/
• 71_blackwell_gemm_with_collective_builder/
• 72_blackwell_narrow_precision_gemm/
• 73_blackwell_gemm_preferred_cluster/
• 74_blackwell_gemm_streamk/
• 75_blackwell_grouped_gemm/
• 76_blackwell_conv/
• 77_blackwell_fmha/
• 78_blackwell_emulated_bf16x9_gemm/
• 79_blackwell_geforce_gemm/
• 80_blackwell_geforce_sparse_gemm/
• 81_blackwell_gemm_blockwise/
• 82_blackwell_distributed_gemm/
• 83_blackwell_sparse_gemm/
• 84_blackwell_narrow_precision_sparse_gemm/
• 88_hopper_fmha/
• CMakeLists.txt
• common/
• cute/
• python/
• README.md