| Name | Last modified | Size | Description | |
|---|---|---|---|---|
| Parent Directory | - | |||
| cpp.py | 2025-07-13 15:42 | 213K | ||
| triton.py | 2025-07-13 15:42 | 169K | ||
| wrapper.py | 2025-07-13 15:42 | 113K | ||
| cpp_wrapper_cpu.py | 2025-07-13 15:42 | 105K | ||
| common.py | 2025-07-13 15:42 | 90K | ||
| simd.py | 2025-07-13 15:42 | 81K | ||
| cpp_gemm_template.py | 2025-07-13 15:42 | 64K | ||
| halide.py | 2025-07-13 15:42 | 61K | ||
| cpp_micro_gemm.py | 2025-07-13 15:42 | 56K | ||
| triton_combo_kernel.py | 2025-07-13 15:42 | 40K | ||
| cpp_flex_attention_template.py | 2025-07-13 15:42 | 39K | ||
| cpp_wrapper_cpu_array_ref.py | 2025-07-13 15:42 | 39K | ||
| cpp_prefix.h | 2025-07-13 15:42 | 32K | ||
| cpp_utils.py | 2025-07-13 15:42 | 29K | ||
| mps.py | 2025-07-13 15:42 | 26K | ||
| memory_planning.py | 2025-07-13 15:42 | 24K | ||
| cpp_template_kernel.py | 2025-07-13 15:42 | 24K | ||
| simd_kernel_features.py | 2025-07-13 15:42 | 23K | ||
| cpp_wrapper_gpu.py | 2025-07-13 15:42 | 21K | ||
| cpp_grouped_gemm_template.py | 2025-07-13 15:42 | 20K | ||
| multi_kernel.py | 2025-07-13 15:42 | 15K | ||
| debug_utils.py | 2025-07-13 15:42 | 11K | ||
| cpp_bmm_template.py | 2025-07-13 15:42 | 9.1K | ||
| triton_utils.py | 2025-07-13 15:42 | 7.2K | ||
| triton_split_scan.py | 2025-07-13 15:42 | 7.1K | ||
| block_analysis.py | 2025-07-13 15:42 | 6.5K | ||
| cuda_combined_scheduling.py | 2025-07-13 15:42 | 4.8K | ||
| cpp_template.py | 2025-07-13 15:42 | 4.7K | ||
| aoti_hipify_utils.py | 2025-07-13 15:42 | 1.3K | ||
| cpu_device_op_overrides.py | 2025-07-13 15:42 | 632 | ||
| mps_device_op_overrides.py | 2025-07-13 15:42 | 467 | ||
| __init__.py | 2025-07-13 15:42 | 0 | ||
| xpu/ | 2025-07-13 15:42 | - | ||
| rocm/ | 2025-07-13 15:42 | - | ||
| cuda/ | 2025-07-13 15:42 | - | ||
| aoti_runtime/ | 2025-07-13 15:42 | - | ||
| __pycache__/ | 2025-07-13 15:42 | - | ||