pytorch / pytorch/executorch

Handle 4-bit CoreML affine quantization via PT2E

Open
#9,649 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

🚀 The feature, motivation and pitch

Handle 4-bit affine quantization (channelwise and groupwise) via PT2E. Remove flow that uses the partitioner.

Alternatives

No response

Additional context

No response

RFC (Optional)

No response

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

The issue names PT2E, CoreML affine quantization, and the partitioner flow but no files or tests. Start by locating the PT2E CoreML quantization and partitioner entry points; done means channelwise and groupwise 4-bit affine quantization works through PT2E and the partitioner flow is removed.

Written by the indexing model from the issue text.

Assessment

Domain
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.