Skip to content

Bump PyTorch pin to nightly dev20260614#20275

Open
pytorchupdatebot wants to merge 1 commit into
mainfrom
automated/pytorch-pin-bump-dev20260614
Open

Bump PyTorch pin to nightly dev20260614#20275
pytorchupdatebot wants to merge 1 commit into
mainfrom
automated/pytorch-pin-bump-dev20260614

Conversation

@pytorchupdatebot

@pytorchupdatebot pytorchupdatebot commented Jun 15, 2026

Copy link
Copy Markdown
Collaborator

Summary

Automated weekly PyTorch pin bump.

  • Updates NIGHTLY_VERSION in torch_pin.py to dev20260614
  • 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 Jun 15, 2026
@pytorch-bot

pytorch-bot Bot commented Jun 15, 2026 •
edited
Loading

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20275

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

❌ 98 New Failures, 131 Cancelled Jobs, 4 Unrelated Failures, 19 Unclassified Failures

As of commit 57d4c87 with merge base e88fd04 (image):

NEW FAILURES - The following jobs have failed:

UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:

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

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

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 Jun 15, 2026
@github-actions

github-actions Bot commented Jun 15, 2026

Copy link
Copy Markdown

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

pytorchupdatebot commented Jun 15, 2026

Copy link
Copy Markdown
Collaborator Author

@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/27541872571

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

claude Bot commented Jun 15, 2026 •
edited
Loading

Copy link
Copy Markdown

Claude finished @pytorchupdatebot's task in 2m 32s —— View job

CI Fix Attempt 1/3 — Stopping: requires architectural decision

I investigated the trunk failures (ignoring jobs marked FLAKY/CANCELLED). The non-flaky failures across Linux aarch64, macOS, OpenVINO, and setup jobs all share one root cause, and it is not an ExecuTorch code bug or a c10 sync issue that I can safely patch.

Root cause: PyTorch nightly now requires C++20

The dev20260614 nightly's installed headers use C++20-only language features, but ExecuTorch builds with C++17 everywhere (CMAKE_CXX_STANDARD 17, .buckconfig -std=c++17, .lintrunner.toml --std=c++17).

Two distinct C++20 features now appear in upstream headers:

  1. Concepts in ATen/NumericUtils.h (hits GCC/Linux builds):

    template <std::integral T>          // error: 'std::integral' has not been declared
inline C10_HOST_DEVICE bool _isnan(T) { ... }
template <std::floating_point T>    // error: 'std::floating_point' has not been declared

    Under C++17 the concept constraints don't parse, which cascades into the misleading vec128_half_neon.h:273 / vec_base.h:922: missing template arguments before '(' token errors seen in the Dr. CI summary.

  2. std::numbers in c10/util/MathConstants.h (hits Clang/macOS builds):

    return static_cast<T>(std::numbers::e_v<double>);  // error: no member named 'numbers' in namespace 'std'

    <numbers> is a C++20 header.

Why I'm stopping here

Per my instructions, if a pin bump introduces a major BC-breaking change requiring architectural discussion, I should flag it and not attempt a fix. This qualifies:

  • The fix is to raise ExecuTorch's C++ standard from 17 to 20, which touches the entire build system (CMake presets, Buck config, lintrunner, every backend's CMAKE_CXX_STANDARD, plus the documented C++17 minimum) and affects downstream embedded/edge consumers who may be pinned to C++17 toolchains.
  • This is not a localized ExecuTorch-vs-new-API adaptation; it's a language-standard bump that the project maintainers need to decide on and coordinate.
  • The constraints explicitly forbid me from working around it by editing runtime/core/portable_type/c10/ (these are correctly-synced upstream headers) or the pin files.

Recommendation

This pin bump should be held for human review. The decision is whether to:

  1. Move ExecuTorch to C++20 (largest blast radius, but follows upstream), or
  2. Ask the PyTorch side to keep these headers C++17-compatible (guard the concepts/std::numbers usage), or
  3. Skip/pin around this particular nightly.

cc @jakeszwe — this needs a maintainer decision on the C++17 → C++20 question; I did not modify any files.

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

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