pytorch / executorch

On-device AI across mobile, embedded and edge for PyTorch
https://pytorch.org/executorch/
Other
2.2k stars 368 forks source link

[DO NOT COMMIT] Repro stride issue #6967

Open dvorjackz opened 2 days ago

dvorjackz commented 2 days ago

Summary

[PLEASE REMOVE] See CONTRIBUTING.md's Pull Requests for ExecuTorch PR guidelines.

[PLEASE REMOVE] If this PR closes an issue, please add a Fixes #<issue-id> line.

[PLEASE REMOVE] If this PR introduces a fix or feature that should be the upcoming release notes, please add a "Release notes: " label. For a list of available release notes labels, check out CONTRIBUTING.md's Pull Requests.

Test plan

[PLEASE REMOVE] How did you test this PR? Please write down any manual commands you used and note down tests that you have written if applicable.

pytorch-bot[bot] commented 2 days ago

:link: Helpful Links

:test_tube: See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6967

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

:heavy_exclamation_mark: 1 Active SEVs

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

:x: 25 New Failures, 4 Unrelated Failures

As of commit bda391f830e0f6dc873ae6a68563076eb979ded0 with merge base 809a1a5f1a80892a16ac173a10718bbbc0154279 (image):

NEW FAILURES - The following jobs have failed:

* [Build documentation / build (buck2) / Build doc](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225440067) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403613/job/33225440067)) `##[error]No files were found with the provided path: /home/ec2-user/actions-runner/_work/_temp/artifacts/. No artifacts will be uploaded.` * [Check Labels / Check labels](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225438968) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403199/job/33225438968)) `RuntimeError: Error checking labels: PR does not have required labels` * [Lint / lintrunner / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225440498) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403615/job/33225440498)) `>>> Lint for examples/models/llama3_2_vision/text_decoder/model.py:` * [pull / test-binary-size-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225446478) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225446478)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-binary-size-linux-gcc / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225447069) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225447069)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-custom-ops-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225442951) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225442951)) `##[error]fatal: unable to access 'https://review.mlplatform.org/tosa/serialization_lib/': The requested URL returned error: 502` * [pull / test-eval_llama-mmlu-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225448268) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225448268)) `##[error]fatal: unable to access 'https://review.mlplatform.org/ml/ethos-u/ethos-u-core-driver/': The requested URL returned error: 502` * [pull / test-eval_llama-wikitext-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225448569) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225448569)) `##[error]fatal: unable to access 'https://review.mlplatform.org/ml/ethos-u/ethos-u-core-driver/': The requested URL returned error: 502` * [pull / test-llama_runner_eager-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225448839) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225448839)) `##[error]fatal: unable to access 'https://review.mlplatform.org/ml/ethos-u/ethos-u-core-driver/': Failed to connect to review.mlplatform.org port 443 after 130876 ms: Couldn't connect to server` * [pull / test-llama-runner-linux-android / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225445900) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225445900)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-llama-runner-qnn-linux (fp32, qnn) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225449145) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225449145)) `##[error]fatal: unable to access 'https://review.mlplatform.org/ml/ethos-u/ethos-u-core-driver/': Failed to connect to review.mlplatform.org port 443 after 130043 ms: Couldn't connect to server` * [pull / test-llava-runner-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225447318) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225447318)) `test_llava_export` * [pull / test-models-linux (buck2, mv3, portable, linux.2xlarge, 90) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225452558) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225452558)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-models-linux (buck2, mv3, xnnpack-quantization-delegation, linux.2xlarge, 90) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225452864) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225452864)) `##[error]fatal: unable to access 'https://review.mlplatform.org/ml/ethos-u/ethos-u-core-driver/': The requested URL returned error: 502` * [pull / test-models-linux (cmake, mv3, xnnpack-quantization-delegation, linux.2xlarge, 90) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225453421) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225453421)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-models-linux (cmake, vit, portable, linux.2xlarge, 90) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225453681) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225453681)) `##[error]fatal: unable to access 'https://review.mlplatform.org/ml/ethos-u/ethos-u-core-driver/': The requested URL returned error: 502` * [pull / test-models-linux (cmake, vit, xnnpack-quantization-delegation, linux.2xlarge, 90) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225453941) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225453941)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-phi-3-mini-runner-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225449624) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225449624)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-pybind-build-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225447675) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225447675)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-quantized-aot-lib-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225448004) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225448004)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / test-selective-build-linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225449396) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225449396)) `##[error]fatal: unable to access 'https://review.mlplatform.org/ml/ethos-u/ethos-u-core-driver/': The requested URL returned error: 502` * [pull / test-setup-linux-gcc / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225446141) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225446141)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / unittest / linux / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225449870) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225449870)) `##[error]error: RPC failed; HTTP 502 curl 22 The requested URL returned error: 502` * [pull / unittest / macos / macos-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225450120) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225450120)) `##[error]fatal: unable to access 'https://review.mlplatform.org/tosa/serialization_lib/': The requested URL returned error: 502` * [pull / unittest-arm / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225442160) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225442160)) `RuntimeError: Command docker exec -t df5a3b0efe3db814e5de170d723c97d6d121bc41a55251938290668089887d57 /exec failed with exit code 1`

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

* [pull / test-llama-runner-linux (bf16, portable) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225444825) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225444825)) ([similar failure](https://hud.pytorch.org/pytorch/executorch/commit/bda391f830e0f6dc873ae6a68563076eb979ded0#33225446811)) `##[error]No files were found with the provided path: /home/ec2-user/actions-runner/_work/_temp/artifacts/. No artifacts will be uploaded.` * [pull / test-llama-runner-linux (fp32, xnnpack+custom) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225445611) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225445611)) ([similar failure](https://hud.pytorch.org/pytorch/executorch/commit/bda391f830e0f6dc873ae6a68563076eb979ded0#33225446811)) `##[error]No files were found with the provided path: /home/ec2-user/actions-runner/_work/_temp/artifacts/. No artifacts will be uploaded.` * [pull / test-llama-runner-linux (fp32, xnnpack+custom+qe) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225446811) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225446811)) ([similar failure](https://hud.pytorch.org/pytorch/executorch/commit/bda391f830e0f6dc873ae6a68563076eb979ded0#33225443270)) `##[error]No files were found with the provided path: /home/ec2-user/actions-runner/_work/_temp/artifacts/. No artifacts will be uploaded.`

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

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

* [pull / test-llama-runner-linux (bf16, custom) / linux-job](https://hud.pytorch.org/pr/pytorch/executorch/6967#33225443270) ([gh](https://github.com/pytorch/executorch/actions/runs/11921403621/job/33225443270)) ([trunk failure](https://hud.pytorch.org/pytorch/executorch/commit/809a1a5f1a80892a16ac173a10718bbbc0154279#33219674083)) `##[error]No files were found with the provided path: /home/ec2-user/actions-runner/_work/_temp/artifacts/. No artifacts will be uploaded.`

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

github-actions[bot] commented 2 days ago

This PR needs a release notes: label

If your changes are user facing and intended to be a part of release notes, please use a label starting with release notes:.

If not, please add the topic: not user facing label.

To add a label, you can comment to pytorchbot, for example @pytorchbot label "topic: not user facing"

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