apple/coreai-optimization

A library for PyTorch model compression and optimizations for deployment via Core AI on Apple silicon.

Stars: 131
Forks: 36
Open beginner issues: 0
Indexed issues: 4
Avg merge: 2d 13h
Merged PRs (30d): 24

Dominant language: Python
License: BSD-3-Clause
Last GitHub push: Sep 19, 2026
Latest indexed: Sep 14, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

3 open issues indexed

[Bug]: ChannelStructured pruning crashes with RuntimeError on 1D tensors (PyTorch sum(dim=[]) scalar collapse) Open

apple/coreai-optimization#107 · 3 comments · 1 assignee · Opened Sep 17, 2026
[Bug]: EagerQuantizer maps root module weight fake-quantizers to "parametrizations", silently dropping QATSchedule and breaking training transitions Open

apple/coreai-optimization#100 · 1 assignee · Opened Sep 16, 2026
FP16 casting pass does not guard against activation-level overflow (softplus, exp, logsumexp) Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

apple/coreai-optimization#7 · 2 comments · Opened Jun 21, 2026

A short digest of beginner-friendly GitHub issues.