| .. |
|
aoti_runtime
|
[AOTI] Save data sizes to constants_info (#154534)
|
2025-05-29 06:39:13 +00:00 |
|
cuda
|
[submodule] upgrade cutlass version to 4.2.1 and completely resolved python/cutlass name collision (#164156)
|
2025-09-30 17:04:57 +00:00 |
|
cutedsl
|
Refactor Provenance Tracking (#163378)
|
2025-09-25 22:55:59 +00:00 |
|
mtia
|
[Re-land][Inductor] Support native Inductor as backend for MTIA (#159211)
|
2025-07-29 17:03:24 +00:00 |
|
rocm
|
Refactor Provenance Tracking (#163378)
|
2025-09-25 22:55:59 +00:00 |
|
xpu
|
[Inductor] Update Intel Triton for PyTorch 2.9. (#161050)
|
2025-08-25 17:18:19 +00:00 |
|
__init__.py
|
|
|
|
aoti_hipify_utils.py
|
[BE][3/16] fix typos in torch/ (torch/_inductor/) (#156313)
|
2025-06-23 02:57:12 +00:00 |
|
block_analysis.py
|
[Inductor] Restrict block analysis to only match integer dims and strides (#149615)
|
2025-06-24 22:43:12 +00:00 |
|
common.py
|
Revert "Add num_store to inductor_meta and use it to scale persistent reduction x block (#162446)"
|
2025-10-01 16:23:03 +00:00 |
|
cpp_bmm_template.py
|
|
|
|
cpp_flex_attention_template.py
|
[FlexAttn] Fix Paged Attention Accuracy via Upper Mask Mod and Prevent Invalid Memory Access (#160861)
|
2025-08-30 04:50:23 +00:00 |
|
cpp_gemm_template.py
|
[CPU][GEMM Template] Improve A16W8 performance (#162479)
|
2025-09-18 01:28:37 +00:00 |
|
cpp_grouped_gemm_template.py
|
|
|
|
cpp_micro_gemm.py
|
Add SVE128 ISA (#158932)
|
2025-09-29 14:49:19 +00:00 |
|
cpp_template_kernel.py
|
[AOTInductor] ABI-Compatibility for RecordFunction. (#159842)
|
2025-08-15 21:45:47 +00:00 |
|
cpp_template.py
|
[AOTInductor] ABI-Compatibility for RecordFunction. (#159842)
|
2025-08-15 21:45:47 +00:00 |
|
cpp_utils.py
|
[doc]: Small typos (#162982)
|
2025-09-16 17:42:19 +00:00 |
|
cpp_wrapper_cpu_array_ref.py
|
[Inductor-FX] Support IndexPutFallback (#162863)
|
2025-09-16 08:52:47 +00:00 |
|
cpp_wrapper_cpu.py
|
[aoti] AOTI mingw cross compilation (#163188)
|
2025-10-01 02:22:06 +00:00 |
|
cpp_wrapper_gpu.py
|
[aoti] AOTI mingw cross compilation (#163188)
|
2025-10-01 02:22:06 +00:00 |
|
cpp_wrapper_mps.py
|
[aoti][mps] Initialize mps kernels first (#159753)
|
2025-08-06 07:54:29 +00:00 |
|
cpp.py
|
[1/N] Fix ruff warnings (#164333)
|
2025-10-01 16:48:32 +00:00 |
|
cpu_device_op_overrides.py
|
[Inductor][CPP] Reuse the pre-existing kernel for the same kernels (#158404)
|
2025-09-16 01:54:24 +00:00 |
|
cuda_combined_scheduling.py
|
Add cutedsl template support to compile (#160108)
|
2025-08-18 04:37:15 +00:00 |
|
debug_utils.py
|
|
|
|
halide.py
|
[Inductor] Add DeviceAssert op to enable device-side assertion in torch.compile (#160677)
|
2025-08-28 18:57:34 +00:00 |
|
memory_planning.py
|
Fix unbacked symint and memory leak in inductor memory planning (#159839)
|
2025-08-11 17:16:15 +00:00 |
|
mps_device_op_overrides.py
|
[aoti] Initial Metal support (#153959)
|
2025-05-23 05:45:35 +00:00 |
|
mps.py
|
[MPS] Add igamma/igammac ops (#161927)
|
2025-09-02 20:52:02 +00:00 |
|
multi_kernel.py
|
[multi-kernel] shape-similarity kernel selection (#163090)
|
2025-09-23 21:00:47 +00:00 |
|
python_wrapper_mtia.py
|
[Re-land][Inductor] Support native Inductor as backend for MTIA (#159211)
|
2025-07-29 17:03:24 +00:00 |
|
segmented_tree.py
|
[inductor] dont reuse buffers if it affects peak (#145883) (#159530)
|
2025-08-19 19:02:56 +00:00 |
|
simd_kernel_features.py
|
skip non memory deps in memory estimator (#164294)
|
2025-10-01 02:44:58 +00:00 |
|
simd.py
|
[inductor][templates] Template hooks should be finalised inside a kernel context (#164229)
|
2025-09-30 17:50:59 +00:00 |
|
subgraph.py
|
[inductor][mm] restructure decompose k (#161026)
|
2025-08-28 20:14:41 +00:00 |
|
triton_combo_kernel.py
|
[Inductor] Fix ComboKernels failing due to missing helper functions (#162759)
|
2025-09-12 20:01:06 +00:00 |
|
triton_split_scan.py
|
[inductor] propagate shapes in CSEVariable (#152198)
|
2025-08-19 16:46:38 +00:00 |
|
triton_utils.py
|
Revert "[inductor] Fix issue with scalar arg handling" (#163737)
|
2025-09-24 07:33:12 +00:00 |
|
triton.py
|
Revert "Add num_store to inductor_meta and use it to scale persistent reduction x block (#162446)"
|
2025-10-01 16:23:03 +00:00 |
|
wrapper_fxir.py
|
[Inductor-FX] Generalize FloorDiv conversion to handle more complex launch grids. Remove python_slow grid mode. (#163828)
|
2025-09-30 16:47:49 +00:00 |
|
wrapper.py
|
[dynamic shapes] unbacked-safe slicing (#161414)
|
2025-09-30 01:15:19 +00:00 |
f7ab8a2710