[Inductor][Tritonparse] Call `jit_post_compile_hook` within Inductor Triton Kernel compile path #161443

NikhilAPatel · 2025-08-25T21:37:54Z

Summary: Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke knobs.runtime.jit_post_compile_hook if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 config variable.

Reviewed By: davidberard98

Differential Revision: D80624932

cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @chenyang78 @kadeng @muchulee8 @amjames @chauhang @aakhundov @coconutruben

pytorch-bot · 2025-08-25T21:37:57Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/161443

📄 Preview Python docs built from this PR
📄 Preview C++ docs built from this PR
❓ Need help or want to give feedback on the CI? Visit the bot commands wiki or our office hours

Note: Links to docs will display an error until the docs builds have been completed.

✅ You can merge normally! (8 Unrelated Failures)

As of commit 02168bb with merge base e6aa728 ():

FLAKY - The following job failed but was likely due to flakiness present on trunk:

trunk / macos-py3-arm64 / test (default, 1, 3, macos-m1-stable) (gh) (similar failure)
Build left local git repository checkout dirty

BROKEN TRUNK - The following jobs failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

inductor / cuda12.8-py3.10-gcc9-sm86 / test (inductor_torchbench, 1, 2, linux.g5.4xlarge.nvidia.gpu) (gh) (trunk failure)
functorch_maml_omniglot
inductor / cuda12.8-py3.10-gcc9-sm86 / test (inductor_torchbench, 2, 2, linux.g5.4xlarge.nvidia.gpu) (gh) (trunk failure)
maml_omniglot
inductor / linux-jammy-cpu-py3.9-gcc11-inductor / test (cpu_inductor_torchbench, 1, 2, linux.8xlarge.amx) (gh) (trunk failure)
functorch_maml_omniglot
inductor / linux-jammy-cpu-py3.9-gcc11-inductor / test (cpu_inductor_torchbench, 2, 2, linux.8xlarge.amx) (gh) (trunk failure)
maml_omniglot
inductor / linux-jammy-cpu-py3.9-gcc11-inductor / test (dynamic_cpu_inductor_torchbench, 1, 2, linux.8xlarge.amx) (gh) (trunk failure)
functorch_maml_omniglot
inductor / linux-jammy-cpu-py3.9-gcc11-inductor / test (dynamic_cpu_inductor_torchbench, 2, 2, linux.8xlarge.amx) (gh) (trunk failure)
maml_omniglot
inductor / linux-jammy-cpu-py3.9-gcc11-inductor / test (inductor_torchbench_cpu_smoketest_perf, 1, 1, linux.24xl.spr-metal) (gh) (trunk failure)
Process completed with exit code 1.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

facebook-github-bot · 2025-08-25T21:38:03Z

This pull request was exported from Phabricator. Differential Revision: D80624932

Summary: X-link: pytorch/pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98 Differential Revision: D80624932

FindHao

LGTM! please fix the lint error before land.

…th (#83) Summary: X-link: pytorch/pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98 Differential Revision: D80624932

…Triton Kernel compile path (pytorch#161443) Summary: X-link: meta-pytorch/tritonparse#83 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98 Differential Revision: D80624932

facebook-github-bot · 2025-08-25T21:50:54Z

This pull request was exported from Phabricator. Differential Revision: D80624932

…th (#83) Summary: Pull Request resolved: #83 X-link: pytorch/pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

facebook-github-bot · 2025-08-25T21:54:36Z

This pull request was exported from Phabricator. Differential Revision: D80624932

…Triton Kernel compile path (pytorch#161443) Summary: X-link: meta-pytorch/tritonparse#83 Pull Request resolved: pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

…th (#83) Summary: X-link: pytorch/pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

…Triton Kernel compile path (pytorch#161443) Summary: X-link: meta-pytorch/tritonparse#83 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

…th (#83) Summary: Pull Request resolved: #83 X-link: pytorch/pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

facebook-github-bot · 2025-08-25T22:10:53Z

This pull request was exported from Phabricator. Differential Revision: D80624932

…Triton Kernel compile path (pytorch#161443) Summary: X-link: meta-pytorch/tritonparse#83 Pull Request resolved: pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

…th (#83) Summary: X-link: pytorch/pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

…Triton Kernel compile path (pytorch#161443) Summary: X-link: meta-pytorch/tritonparse#83 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

…Triton Kernel compile path (pytorch#161443) Summary: X-link: meta-pytorch/tritonparse#83 Pull Request resolved: pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

…th (#83) Summary: Pull Request resolved: #83 X-link: pytorch/pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932

facebook-github-bot · 2025-08-25T23:38:17Z

This pull request was exported from Phabricator. Differential Revision: D80624932

…th (#83) Summary: Pull Request resolved: #83 X-link: pytorch/pytorch#161443 Since Inductor skips JIT compilation for Triton kernels, we need to manually invoke `knobs.runtime.jit_post_compile_hook` if one exists. Here, we do this to enable Tritonparse to extract launch metadata from Inductor launched kernels. We can control whether or not Inductor will run the hook with a new `TORCHINDUCTOR_RUN_JIT_POST_COMPILE_HOOK=1 ` config variable. Reviewed By: davidberard98, FindHao Differential Revision: D80624932 fbshipit-source-id: 57cd14f3facf053fe1c02b15f04f0ea4c1b68198

facebook-github-bot · 2025-08-26T06:16:49Z

@pytorchbot merge

(Initiating merge automatically since Phabricator Diff has merged)

pytorchmergebot · 2025-08-26T06:19:01Z

Merge started

Your change will be merged once all checks pass (ETA 0-4 Hours).

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging

Check the merge workflow status
here

pytorch-bot bot added ciflow/inductor module: inductor labels Aug 25, 2025

facebook-github-bot added the fb-exported label Aug 25, 2025

NikhilAPatel added the topic: not user facing topic category label Aug 25, 2025

NikhilAPatel requested review from FindHao and davidberard98 August 25, 2025 21:38

FindHao approved these changes Aug 25, 2025

View reviewed changes

pytorch-bot bot added the ciflow/trunk Trigger trunk jobs on your pull request label Aug 25, 2025

NikhilAPatel force-pushed the export-D80624932 branch 2 times, most recently from f8b9b61 to b481724 Compare August 25, 2025 21:50

NikhilAPatel force-pushed the export-D80624932 branch from b481724 to 76b59bc Compare August 25, 2025 21:54

NikhilAPatel force-pushed the export-D80624932 branch from 76b59bc to 147b22c Compare August 25, 2025 22:06

NikhilAPatel force-pushed the export-D80624932 branch from 147b22c to 395e435 Compare August 25, 2025 22:10

NikhilAPatel force-pushed the export-D80624932 branch from 395e435 to ab203df Compare August 25, 2025 23:32

NikhilAPatel force-pushed the export-D80624932 branch from ab203df to 02168bb Compare August 25, 2025 23:38

pytorchmergebot added the merging label Aug 26, 2025

pytorchmergebot closed this in 6aef9f3 Aug 26, 2025

pytorchmergebot added Merged and removed merging labels Aug 26, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[Inductor][Tritonparse] Call `jit_post_compile_hook` within Inductor Triton Kernel compile path #161443

[Inductor][Tritonparse] Call `jit_post_compile_hook` within Inductor Triton Kernel compile path #161443

Uh oh!

NikhilAPatel commented Aug 25, 2025 •

edited by pytorch-bot bot

Loading

Uh oh!

pytorch-bot bot commented Aug 25, 2025 •

edited

Loading

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

FindHao left a comment

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 26, 2025

Uh oh!

pytorchmergebot commented Aug 26, 2025

Uh oh!

Uh oh!

[Inductor][Tritonparse] Call jit_post_compile_hook within Inductor Triton Kernel compile path #161443

[Inductor][Tritonparse] Call jit_post_compile_hook within Inductor Triton Kernel compile path #161443

Uh oh!

Conversation

NikhilAPatel commented Aug 25, 2025 • edited by pytorch-bot bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot bot commented Aug 25, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/161443

✅ You can merge normally! (8 Unrelated Failures)

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

FindHao left a comment

Choose a reason for hiding this comment

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 25, 2025

Uh oh!

facebook-github-bot commented Aug 26, 2025

Uh oh!

pytorchmergebot commented Aug 26, 2025

Merge started

Uh oh!

Uh oh!

[Inductor][Tritonparse] Call `jit_post_compile_hook` within Inductor Triton Kernel compile path #161443

[Inductor][Tritonparse] Call `jit_post_compile_hook` within Inductor Triton Kernel compile path #161443

NikhilAPatel commented Aug 25, 2025 •

edited by pytorch-bot bot

Loading

pytorch-bot bot commented Aug 25, 2025 •

edited

Loading