openvinotoolkit / openvinotoolkit/nncf

[TorchFX] `quantize_pt2e`: support QAT mode

Open
#3,170 0 comments 0 reactions 0 assignees View on GitHub

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

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 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.