Jason Ansel 2da7fb5320 [inductor] Make generated kernels deterministic (#143951) ... `"compile_id"` had slipped into our generated Triton code (in the metadata), which will defeat caching because the same kernels generated in a different order would not cache hit with eachother. Pull Request resolved: https://github.com/pytorch/pytorch/pull/143951 Approved by: https://github.com/oulgen		2024-12-30 23:35:11 +00:00
..
aoti_runtime	[AOTI][refactor] Separate header codegen (#138882)	2024-10-27 14:14:27 +00:00
cuda	[CUTLASS] fix bugs: extra data_ptr() call, wrong size symbol name, bias symbol not added (#143528)	2024-12-27 23:38:18 +00:00
rocm	remove allow-untyped-defs from _inductor/codegen/rocm/rocm_template_buffer.py (#143870)	2024-12-27 23:28:51 +00:00
xpu	[AOTI XPU] Enable Cpp wraper for Intel GPU. (#135318)	2024-11-26 11:51:32 +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	[Inductor] move block pointer analysis to a new module (#141733)	2024-11-30 23:21:24 +00:00
common.py	[Inductor] Implement primitive Metal compiler (#143893)	2024-12-28 06:58:32 +00:00
cpp_bmm_template.py	[inductor][cpp] Add BMM kernel template for autotuning (#129772)	2024-12-06 04:54:00 +00:00
cpp_flex_attention_template.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
cpp_gemm_template.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
cpp_micro_gemm.py	Simplify & rectify dequantized B buffer loading for AMX GEMM micro-kernel for WoQ int8 case (#140258)	2024-11-22 01:34:06 +00:00
cpp_prefix.h	[16/N] Fix extra warnings brought by clang-tidy-17 (#143714)	2024-12-24 03:29:38 +00:00
cpp_template_kernel.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
cpp_template.py	[AOTI] Remove the non-ABI-compatible mode (part 1) (#138009)	2024-10-17 02:48:26 +00:00
cpp_utils.py	[Inductor][CPP] Fix Data Type issue of frexp (#143746)	2024-12-28 06:00:13 +00:00
cpp_wrapper_cpu_array_ref.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
cpp_wrapper_cpu.py	cpp_wrapper: minimize pybind11 dependency (#143772)	2024-12-30 20:41:02 +00:00
cpp_wrapper_gpu.py	[AOTI] Relax input alignment assertion (#143236)	2024-12-17 00:17:39 +00:00
cpp.py	[Inductor][CPP] Fix Data Type issue of frexp (#143746)	2024-12-28 06:00:13 +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	Prologue Fusion (#134532)	2024-12-13 04:18:25 +00:00
debug_utils.py	Rename convert_arrayref_tensor_to_tensor to copy_arrayref_tensor_to_tensor (#142182)	2024-12-09 22:23:21 +00:00
halide.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
memory_planning.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
mps_device_op_overrides.py	[Inductor] Add MPS device op overrides (#143892)	2024-12-28 02:11:45 +00:00
mps.py	[Inductor] Implement primitive Metal compiler (#143893)	2024-12-28 06:58:32 +00:00
multi_kernel.py	Revert "Use absolute path path.resolve() -> path.absolute() (#129409)"	2024-12-26 17:26:06 +00:00
simd_kernel_features.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
simd.py	[provenance_tracking] Dump inductor_triton_kernel_to_post_grad_nodes.json info in debug_trace (#143055)	2024-12-18 06:51:50 +00:00
triton_combo_kernel.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
triton_split_scan.py	[inductor] Replace set by OrderedSet (#138466)	2024-12-13 16:08:45 +00:00
triton_utils.py	[inductor] Move V.graph.scheduler.current_device to V.graph.current_device (#138252)	2024-10-18 23:05:54 +00:00
triton.py	[inductor] Make generated kernels deterministic (#143951)	2024-12-30 23:35:11 +00:00
wrapper.py	[inductor][invoke_subgraph] Support None/int as input/output of invoke_subgraph (#139373)	2024-12-27 06:46:09 +00:00