pytorch / pytorch/executorch

[torchao] support codebook/LUT in torchao

Open
#9,848 0 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

Support codebook/LUT in torchao flows (eager mode and PT2E). Add quant primitives for codebook/LUT. This is recommendation 2 in post: https://fb.workplace.com/groups/pytorch.edge2.team/permalink/1168405054415345/

Quant primitive work: https://github.com/pytorch/ao/pull/1988

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

Start by reviewing the linked quant primitive work in PR 1988 and the torchao flows named in the issue: eager mode and PT2E. Define what codebook/LUT support and the required quant primitives should cover in both flows; done means those flows support the requested codebook/LUT functionality.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
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.