Fix dangling pointer in TextTokenGenerator non-kv-cache path

[kirklandsign]

Summary:
In the non-kv-cache branch of TextTokenGenerator::generate(), push_back()
on token_data can trigger vector reallocation, but the tensor created via
from_blob still points to the old data address. resize_tensor_ptr only
updates shape metadata, not the data pointer, resulting in a dangling
pointer.

Fix by pre-allocating the vector with reserve() before creating the
tensor, ensuring push_back never triggers reallocation during the
generate loop.

Differential Revision: D99408541

[meta-codesync]

@kirklandsign has exported this pull request. If you are a Meta employee, you can view the originating Diff in D99408541.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18725

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure, 9 Pending

As of commit b5e15c8 with merge base 3d2c853 ():

NEW FAILURE - The following job has failed:

• pull / android / run-emulator (gh)
  The process '/usr/local/lib/android/sdk/platform-tools/adb' failed with exit code 224

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

[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.

[Copilot]

Pull request overview

Fixes a memory-safety issue in the LLM token generation loop when KV-cache is disabled: from_blob() wraps token_data.data(), but subsequent push_back() could reallocate the vector and leave the tensor with a dangling data pointer.

Changes:

• Pre-reserve token_data capacity in the non-KV-cache path to prevent reallocation during generation.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.