restore zero-filled storage when called (#21917)

[JakeStevens]

Summary:

To reduce GPU memory during compilation, ExecuTorch intentionally keeps shape metadata but frees its storage with resize_(0).

The existing workaround restored the zero-filled storage only when called from Inductor’s _unlift_graph. PyTorch 2.13 introduced other cloning paths during AOTI compilation/autotuning. Those paths attempted to clone the shaped tensor while its storage was still zero bytes, producing:

  required storage: 4194304 bytes
  actual storage: 0 bytes

The fix now detects any intentionally emptied KV-cache tensor before examining the caller and restores zero-filled storage

Reviewed By: digantdesai

Differential Revision: D116459495

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21917

• 📄 Preview Python docs built from this PR

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

❌ 4 New Failures

As of commit 507e40e with merge base 080e4a2 ():

NEW FAILURES - The following jobs have failed:

• Cadence Build & Test / hifi-build / hifi4 (gh)
  ##[error]Refusing to check out fork pull request code from a 'pull_request_target' workflow. This workflow runs with the base repository's GITHUB_TOKEN, secrets, default-branch cache scope, and runner access. Fetching and executing a fork's code in that trusted context commonly leads to "pwn request" vulnerabilities. To opt in, review the risks at https://gh.io/securely-using-pull_request_target and set 'allow-unsafe-pr-checkout: true' on the actions/checkout step.
• Cadence Build & Test / vision-build / vision (gh)
  ##[error]Refusing to check out fork pull request code from a 'pull_request_target' workflow. This workflow runs with the base repository's GITHUB_TOKEN, secrets, default-branch cache scope, and runner access. Fetching and executing a fork's code in that trusted context commonly leads to "pwn request" vulnerabilities. To opt in, review the risks at https://gh.io/securely-using-pull_request_target and set 'allow-unsafe-pr-checkout: true' on the actions/checkout step.
• pull / android / run-emulator (gh)
  WARNING | Failed to load snapshot 'default_boot'
• Test CUDA Builds / unittest-cuda / linux-job (gh)
  RuntimeError: Command docker exec -t 86b01c3e4216640d12e5ed5436cd8f78586a81c78043db461b09ebb63af2c9b8 /exec failed with exit code 2

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

[meta-codesync]

@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D116459495.

[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.