CoreML quantization is supported by PyTorch flows (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
All ET CoreML delegate quantization should be supported by PT2E.
Support is missing for:
- int4 quantization (per tensor and per group)
- Palletization
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
Start by locating the ExecuTorch CoreML delegate quantization implementation and its PT2E integration. Trace existing quantization support, then identify the paths and tests covering int4 per-tensor, int4 per-group, and palletization. Done means all three listed cases are supported by the PT2E CoreML flows.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100