Skip to content

Fix lookahead decoding cache buffer size #12725

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 23, 2025

Conversation

sxu
Copy link
Contributor

@sxu sxu commented Jul 22, 2025

Summary: For n-grams we are only storing the suffixes of size n-1. Over sizing the buffer here leads to subsequent memcpy copying too much.

Differential Revision: D78759433

@sxu sxu requested review from lucylq and jackzhxng as code owners July 22, 2025 19:37
Copy link

pytorch-bot bot commented Jul 22, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12725

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

❗ 1 Active SEVs

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

✅ You can merge normally! (1 Unrelated Failure)

As of commit 831688b with merge base 56b0074 (image):

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

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

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

@facebook-github-bot facebook-github-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 Jul 22, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D78759433

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.

Summary:

For n-grams we are only storing the suffixes of size n-1. Over sizing the buffer here leads to subsequent memcpy copying too much.

Reviewed By: limintang, billmguo

Differential Revision: D78759433
@sxu sxu force-pushed the export-D78759433 branch from bb9c25b to 831688b Compare July 23, 2025 03:25
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D78759433

@facebook-github-bot facebook-github-bot merged commit b562f36 into pytorch:main Jul 23, 2025
99 of 101 checks passed
Conarnar pushed a commit to Conarnar/executorch that referenced this pull request Jul 25, 2025
Differential Revision: D78759433

Pull Request resolved: pytorch#12725
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. fb-exported topic: not user facing
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants