openvinotoolkit / openvinotoolkit/nncf
[TorchFX] `quantize_pt2e`: support QAT mode
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 305
- Avg merge
- 1d 9h
- Merged PRs (30d)
- 27
Description
🚀 Feature request
The task is to support QAT for quantize_pt2e: for that, one need to introduce quantize_qat_pt2e aligned with prepare_qat_pt2e
Feature Use Case
QAT for TorchFX backend
Are you going to submit a PR?
- Yes I'd like to help by submitting a PR!
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 reading the linked prepare_qat_pt2e implementation in torch/ao/quantization/quantize_pt2e.py and inspect the existing quantize_pt2e integration in this repository. Determine the required quantize_qat_pt2e entry point and its QAT behavior. Done means TorchFX backend models can use QAT through the new entry point.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100