Handle 4-bit CoreML affine quantization via PT2E
Open
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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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