pytorch/torch/_inductor/codegen
Davide Italiano 8cc415774f [mps/inductor] Introduce a metal approx for erf() and use it. (#145161)
Probably we can do better, but this is a start.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/145161
Approved by: https://github.com/malfet
2025-01-19 02:29:05 +00:00
..
aoti_runtime Revert "cpp_wrapper: Move #includes to per-device header files (#143909)" 2025-01-17 00:36:38 +00:00
cuda PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
rocm PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
xpu Revert "cpp_wrapper: Move #includes to per-device header files (#143909)" 2025-01-17 00:36:38 +00:00
__init__.py
aoti_hipify_utils.py remove allow-untyped-defs from _inductor/codegen/aoti_hipify_utils.py (#143916) 2024-12-27 23:25:37 +00:00
block_analysis.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
common.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_bmm_template.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_flex_attention_template.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_gemm_template.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_grouped_gemm_template.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_micro_gemm.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_prefix.h Remove is_reduced_floating_point from namespace std (#144502) 2025-01-10 03:24:10 +00:00
cpp_template_kernel.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_template.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_utils.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_wrapper_cpu_array_ref.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_wrapper_cpu.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp_wrapper_gpu.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpp.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
cpu_device_op_overrides.py remove allow-untyped-defs from _inductor/codegen/cpu_device_op_overrides.py (#143881) 2024-12-27 04:10:47 +00:00
cuda_combined_scheduling.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
debug_utils.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
halide.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
memory_planning.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
mps_device_op_overrides.py [Inductor] Add MPS device op overrides (#143892) 2024-12-28 02:11:45 +00:00
mps.py [mps/inductor] Introduce a metal approx for erf() and use it. (#145161) 2025-01-19 02:29:05 +00:00
multi_kernel.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
simd_kernel_features.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
simd.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
triton_combo_kernel.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
triton_split_scan.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
triton_utils.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
triton.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00
wrapper.py PEP585 update - torch/_inductor/codegen (#145106) 2025-01-18 06:56:03 +00:00