pytorch / pytorch/executorch

XNNPack linear kernel for group size 16 / padding weights

Open
#14,221 7 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

module: xnnpack
Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

🚀 The feature, motivation and pitch

For models with hidden dims that are indivisible by 32. Padding up to 32 could also work.

Alternatives

No response

Additional context

No response

RFC (Optional)

No response

cc @digantdesai @mcr229 @cbilgin

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the XNNPack linear kernel and its current handling of hidden dimensions; no file or test is named in the issue. Clarify the expected group-size-16 behavior and whether padding weights to 32 is required, then define validation for models whose hidden dimensions are not divisible by 32.

Written by the indexing model from the issue text.

Assessment

Domain
embedded-iot, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.