Skip to content

Comments

Fix thread safety of LLM token buffer in Android JNI#17608

Draft
kirklandsign wants to merge 1 commit intomainfrom
android/fix-llm-token-buffer-thread-safety
Draft

Fix thread safety of LLM token buffer in Android JNI#17608
kirklandsign wants to merge 1 commit intomainfrom
android/fix-llm-token-buffer-thread-safety

Conversation

@kirklandsign
Copy link
Contributor

Summary

The UTF-8 token buffer was a global variable shared across all ExecuTorchLlmJni instances, causing token corruption when multiple LlmModule instances run generate() concurrently. Move the buffer to a local variable in generate() captured by the callback lambda, giving each call its own isolated buffer. This matches the pattern already used by the ASR JNI layer.

Test plan

CI

The UTF-8 token buffer was a global variable shared across all
ExecuTorchLlmJni instances, causing token corruption when multiple
LlmModule instances run generate() concurrently. Move the buffer
to a local variable in generate() captured by the callback lambda,
giving each call its own isolated buffer. This matches the pattern
already used by the ASR JNI layer.
@pytorch-bot
Copy link

pytorch-bot bot commented Feb 21, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17608

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

❌ 4 New Failures

As of commit c02b379 with merge base cf08087 (image):

NEW FAILURES - The following jobs have failed:

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 Feb 21, 2026
@github-actions
Copy link

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.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

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

Development

Successfully merging this pull request may close these issues.

1 participant