Skip to content

Bump PyTorch pin to nightly dev20260426#19148

Open
pytorchupdatebot wants to merge 1 commit intomainfrom
automated/pytorch-pin-bump-dev20260426
Open

Bump PyTorch pin to nightly dev20260426#19148
pytorchupdatebot wants to merge 1 commit intomainfrom
automated/pytorch-pin-bump-dev20260426

Conversation

@pytorchupdatebot
Copy link
Copy Markdown
Collaborator

@pytorchupdatebot pytorchupdatebot commented Apr 27, 2026

Summary

Automated weekly PyTorch pin bump.

  • Updates NIGHTLY_VERSION in torch_pin.py to dev20260426
  • Updates .ci/docker/ci_commit_pins/pytorch.txt to the corresponding nightly commit hash
  • Syncs c10 headers from PyTorch into runtime/core/portable_type/c10/

This PR was created automatically. If CI fails, Claude will attempt to fix issues (up to 3 attempts). If CI still fails, human review will be requested.

cc @jakeszwe

@pytorch-bot pytorch-bot Bot added the ci-no-td label Apr 27, 2026
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Apr 27, 2026 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19148

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 68 New Failures, 168 Cancelled Jobs, 7 Unrelated Failures

As of commit f84a650 with merge base 32a6cec (image):

NEW FAILURES - The following jobs have failed:

CANCELLED JOBS - The following jobs were cancelled. Please retry:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

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

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

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

@meta-cla meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Apr 27, 2026
@github-actions
Copy link
Copy Markdown

github-actions Bot commented Apr 27, 2026

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

@pytorchupdatebot
Copy link
Copy Markdown
Collaborator Author

pytorchupdatebot commented Apr 27, 2026

@claude [ci-fix-attempt 1/3]

The trunk CI workflow has failed on this automated PyTorch pin bump PR.
Failed run: https://github.com/pytorch/executorch/actions/runs/24988067130

Please:

  1. Read the Dr. CI comment on this PR for a summary of which jobs failed and whether they are flaky. Ignore failures marked as FLAKY.
  2. Use your CI tools to download the failure logs for the non-flaky failing jobs
  3. Identify the root cause of the failure
  4. If this is a build or test failure caused by PyTorch API changes, fix the ExecuTorch code to be compatible with the new PyTorch version
  5. If this is a c10 header sync issue, the headers have already been synced by the pin bump script — the issue is likely in ExecuTorch code that uses those headers
  6. Run lintrunner -a on any files you change
  7. Push your fix as a new commit to this PR branch

Important constraints:

  • Do NOT modify torch_pin.py or .ci/docker/ci_commit_pins/pytorch.txt — the pin itself is correct
  • Do NOT modify files under runtime/core/portable_type/c10/ unless the sync introduced a new API that ExecuTorch code needs to adapt to
  • Focus on fixing ExecuTorch code to be compatible with the new PyTorch APIs
  • If this is a major BC-breaking change that requires architectural discussion, say so clearly and stop — do not attempt a fix

@claude
Copy link
Copy Markdown

claude Bot commented Apr 27, 2026 •
edited
Loading

Claude finished @pytorchupdatebot's task in 30m 13s —— View job

CI Fix Attempt (1/3)

  • Analyze Dr. CI comment to categorize failures
  • Download and analyze failure logs for non-flaky jobs
  • Identify root cause of failures
  • Implement fixes locally
  • Run lintrunner (blocked by sandbox permissions)
  • Push fix commit (blocked by "Meta CLA Check" branch protection rule)

Root Cause Analysis

I analyzed logs from representative failing jobs across all 3 failure categories. All failures are caused by upstream PyTorch nightly changes, not by ExecuTorch code.

Category ~Jobs Root Cause Fix
fbgemm AVX512 ~35 Linux x86 PyTorch nightly's fbgemm submodule has inline assembly incompatible with CI compilers (clang-12/gcc-11) USE_FBGEMM=0 — ET never uses fbgemm
SVE not found 3 aarch64 docker New FindARM.cmake check rejects builds on Graviton2 (no SVE) BUILD_IGNORE_SVE_UNAVAILABLE=1
torchvision::nms ~13 macOS torchvision release/0.26 (for torch 2.11) incompatible with torch 2.13.0a0 nightly Update torchvision/torchaudio to main branch

Fix (commit ready locally, cannot push)

The push is blocked by the repository's "Meta CLA Check" branch protection rule. The fix needs to be applied manually or by a user with bypass permissions. Here are the exact changes needed in 2 files:

.ci/docker/common/install_pytorch.sh 
   export _GLIBCXX_USE_CXX11_ABI=1
+  export USE_FBGEMM=0
+  export BUILD_IGNORE_SVE_UNAVAILABLE=1
   # Then build and install PyTorch
   conda_run python setup.py bdist_wheel
   pip_install "$(echo dist/*.whl)"
 
   # Grab the pinned audio and vision commits from PyTorch
-  TORCHAUDIO_VERSION=release/2.11
+  TORCHAUDIO_VERSION=main
   export TORCHAUDIO_VERSION
-  TORCHVISION_VERSION=release/0.26
+  TORCHVISION_VERSION=main
   export TORCHVISION_VERSION
.ci/scripts/utils.sh 
-    USE_DISTRIBUTED=1 python setup.py bdist_wheel
+    USE_DISTRIBUTED=1 USE_FBGEMM=0 BUILD_IGNORE_SVE_UNAVAILABLE=1 python setup.py bdist_wheel
     pip install "$(echo dist/*.whl)"
 ...
   # Grab the pinned audio and vision commits from PyTorch
-  TORCHAUDIO_VERSION=release/2.11
+  TORCHAUDIO_VERSION=main
   export TORCHAUDIO_VERSION
-  TORCHVISION_VERSION=release/0.26
+  TORCHVISION_VERSION=main
   export TORCHVISION_VERSION

Why these fixes are safe

  1. USE_FBGEMM=0: ExecuTorch has zero build-system references to fbgemm, zero code imports, and zero C++ linkage. The only "fbgemm" mentions in the codebase are comments documenting numerical behavior matching. Disabling it removes ~15 min of unnecessary compilation.

  2. BUILD_IGNORE_SVE_UNAVAILABLE=1: This is the workaround suggested by PyTorch's own error message. SVE optimizations are not needed for ExecuTorch CI.

  3. torchvision/torchaudio main: The current pins (release/0.26 / release/2.11) match torch 2.11, but the nightly is torch 2.13.0a0. The main branch of these libraries tracks nightly compatibility. The matching release branches (release/0.28 / release/2.13) may not exist yet since 2.13 is pre-release.

cc @jakeszwe — Could you or someone with push access apply this fix? The commit is ready locally (db0e7ee) but the "Meta CLA Check" branch protection rule prevents claude[bot] from pushing.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@JacobSzwejbka JacobSzwejbka Awaiting requested review from JacobSzwejbka JacobSzwejbka is a code owner

@lucylq lucylq Awaiting requested review from lucylq lucylq is a code owner

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

ci/pytorch-pin-bump ci-no-td CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@pytorchupdatebot @pytorchbot