CORTEX_M: Add Packed int4 support
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
Relates to https://github.com/pytorch/executorch/issues/16040. Add support for packed int4 for all ops where CMSIS-NN supports it in the quantizer/ c++ kernels/ passes when the quantizer supports general configuration.
This will likely also require some extra weight clustering in the lowering to get correct weights.
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 with related issue #16040, then inspect the quantizer, C++ kernels, passes, and lowering mentioned in the issue, along with the packed int4 operations supported by CMSIS-NN. Done means packed int4 support is available for all applicable CMSIS-NN operations, general quantizer configuration works, and lowered weights are correctly clustered.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python
- 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