mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00

Files

drisspg de3da77cf7 Thread deterministic config vars to subproc compilation (#165729 )

# Summary

TIL (AFTER WAYYYY TOO MUCH INSANITY), that we do not serialize the full set of configs for the subproc compilation.

I found this while working on Flex-attention determinism: https://github.com/meta-pytorch/attention-gym/pull/168

might be good to audit if we need to thread through any more

Pull Request resolved: https://github.com/pytorch/pytorch/pull/165729
Approved by: https://github.com/shunting314, https://github.com/eellison

2025-10-18 01:25:50 +00:00

caching

Revert "Pyrefly suppressions 2 (#165692 )"

2025-10-17 17:13:04 +00:00

__init__.py

[inductor] Refactor runtime files into torch._inductor.runtime (part 2) (#124553 )

2024-04-22 18:46:20 +00:00

autotune_cache.py

Revert "Pyrefly suppressions 2 (#165692 )"

2025-10-17 17:13:04 +00:00

benchmarking.py

Revert "Pyrefly suppressions 2 (#165692 )"

2025-10-17 17:13:04 +00:00

cache_dir_utils.py

Rename inductor cache (#156128 )

2025-06-17 03:57:18 +00:00

compile_tasks.py

[AARCH64][CD][CUDA13][Triton][PTXAS] Turn on BUILD_BUNDLE_PTXAS=1 (#163988 )

2025-09-30 01:56:12 +00:00

coordinate_descent_tuner.py

Revert "Pyrefly suppressions 2 (#165692 )"

2025-10-17 17:13:04 +00:00

debug_utils.py

Fix inductor memory estimation when a single buf has multiple mutations. Add runtime verification of mem tracking (#159569 )

2025-08-05 19:58:11 +00:00

halide_helpers.py

Remove unused Python variables in torch/[_-a]* (#133492 )

2024-12-12 17:39:14 +00:00

hints.py

Revert "Pyrefly suppressions 2 (#165692 )"

2025-10-17 17:13:04 +00:00

README.md

Add README for torch._inductor.runtime (#141492 )

2024-11-26 14:43:02 +00:00

runtime_utils.py

Revert "Pyrefly suppressions 2 (#165692 )"

2025-10-17 17:13:04 +00:00

static_cuda_launcher.py

Revert "Pyrefly suppressions 2 (#165692 )"

2025-10-17 17:13:04 +00:00

triton_compat.py

Use union syntax in torch/_inductor runtime and fx_passes (#165652 )

2025-10-16 20:51:59 +00:00

triton_helpers.py

[inductor] fix 3d tiled online softmax (#162341 )

2025-09-09 02:59:52 +00:00

triton_heuristics.py

Thread deterministic config vars to subproc compilation (#165729 )

2025-10-18 01:25:50 +00:00

README.md

`torch._inductor.runtime`

This folder contains code needed at runtime by the output code of Inductor. The output code of Inductor will import torch and torch._inductor.runtime, but should not import from other files in torch._inductor.*. Note that this code includes code that is needed to actually perform Triton compilation, but is not needed in the actual, final runtime execution of kernels.

Runtime includes Triton/C++ generated code, which are compiled (sometimes in parallel) when the output code of Inductor is imported. It also includes the autotuning code and heuristics to decide block sizes of generated code.

One of the original motivations for this directory split was so that the Triton compile subprocesses could access Triton and our compiler support code while mocking out most of torch, which can take seconds to import (sometimes more than a Triton compile itself). An abandoned prototype of this can be found here.