Skip to content

Conversation

@manuelcandales
Copy link
Contributor

@manuelcandales manuelcandales commented Feb 4, 2026

This pull request extends support in the Metal backend's 4-bit quantized linear operation (aoti_torch_mps__linear_fp_act_4bit_weight) to the case where the batch size (M) is 1 and the output dimension (N) is not a multiple of 4. To achieve this, we imported the qmv_impl Metal shader from MLX.

[ghstack-poisoned]
@pytorch-bot
Copy link

pytorch-bot bot commented Feb 4, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17187

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

❌ 4 New Failures, 1 Unrelated Failure

As of commit 8ee7d60 with merge base ba6de95 (image):

NEW FAILURES - The following jobs have failed:

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.

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.

2 participants