Fix max seq length bug

[kimishpatel]

Summary:
update cache op was forcing incorrect constraint on sequence length.
Fixing that alongw with fixing export allows us to correctly export the model

Differential Revision: D84562463

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15084

• 📄 Preview Python docs built from this PR

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

❌ 6 New Failures, 3 Unrelated Failures

As of commit f0a030c with merge base c539dfc ():

NEW FAILURES - The following jobs have failed:

• Lint / android-java-format / linux-job (gh)
  RuntimeError: Command docker exec -t dfb148cb864bb40d873862b74fe4318871d2d3e8e580a65c554df9a1c9496efc /exec failed with exit code 1
• pull / android / build-llm-demo / linux-job (gh)
  RuntimeError: Command docker exec -t e4ab1434e3dd347297670384c16ab376419d5c494c315b6a258b7a32a1d3f722 /exec failed with exit code 35
• pull / test-samsung-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 50609e8852102135870613cb550ee89e8fe5afdef190b7769e3ade0c9446acbe /exec failed with exit code 1
• pull / unittest-arm-backend-with-no-fvp (test_pytest_ops) / linux-job (gh)
  RuntimeError: Command docker exec -t af17f2993a485c88e15fe5710745eeb93bf8b82b1809145ca01b2ce0ba1235f9 /exec failed with exit code 1
• Test CUDA Builds / export-voxtral-cuda-artifact / linux-job (gh)
  RuntimeError: Command docker exec -t 72df4d4e1af7f3048abca29eb7c112c351d21c5ef19c0f463731d41364ad6aa7 /exec failed with exit code 2
• trunk / test-llama-runner-mac (fp32, coreml) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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

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

• pull / unittest / windows / windows-job (gh) (trunk failure)
  runtime/test/test_runtime_etdump_gen.py::RuntimeETDumpGenTest::test_etdump_params_with_bytes_and_buffer
• pull / unittest-editable / windows / windows-job (gh) (trunk failure)
  runtime/test/test_runtime_etdump_gen.py::RuntimeETDumpGenTest::test_etdump_params_with_bytes_and_buffer
• trunk / unittest-release / windows / windows-job (gh) (trunk failure)
  runtime/test/test_runtime_etdump_gen.py::RuntimeETDumpGenTest::test_etdump_params_with_bytes_and_buffer

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

[meta-codesync]

@kimishpatel has exported this pull request. If you are a Meta employee, you can view the originating Diff in D84562463.

[github-actions]

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.

[digantdesai]

Review automatically exported from Phabricator review in Meta.

[digantdesai]

let's pull this in 1.0? @GregoryComer

[GregoryComer]

let's pull this in 1.0? @GregoryComer

You can submit a pick request. Though we're only a few days out from release. There will be one final RC build to pick up the pytorch release on Wednesday, but I'm hesitant to merge anything that's not a fix for a catastrophic issue. If you think it's safe and meets that criteria, I'm willing to merge it.

[GregoryComer]

After talking with Digant, I'm willing to merge it (as Digant's judgement is that it is critical). However, it would need to be merged today as soon as possible to make the cut and we'll need to build rc4 and do manual validation by EOD.

[kimishpatel]

After talking with Digant, I'm willing to merge it (as Digant's judgement is that it is critical). However, it would need to be merged today as soon as possible to make the cut and we'll need to build rc4 and do manual validation by EOD.

yeah m trying to land this. test failures seem unrelated but landing internally takes a few hours

[GregoryComer]

@pytorchbot cherry-pic --onto release/1.0 -c critical

[pytorch-bot]

❌ 🤖 pytorchbot command failed:

@pytorchbot: error: argument command: invalid choice: 'cherry-pic' (choose from 'merge', 'revert', 'rebase', 'label', 'drci', 'cherry-pick')

usage: @pytorchbot [-h] {merge,revert,rebase,label,drci,cherry-pick} ...

Try @pytorchbot --help for more info.

[GregoryComer]

@pytorchbot cherry-pick --onto release/1.0 -c critical

[pytorchbot]

Cherry picking #15084

The cherry pick PR is at #15141 and it is recommended to link a critical cherry pick PR with an issue. The following tracker issues are updated:

• [v1.0.0] Release Tracker #14288 (comment)

Details for Dev Infra team

Raised by workflow job