NVIDIA/nvalchemi-toolkit

ALCHEMI Toolkit is a developer toolkit for accelerating training and inference for AI in chemistry and material science.

Stars: 167
Forks: 38
Open beginner issues: 0
Indexed issues: 6
Avg merge: 8d 15h
Merged PRs (30d): 7

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 18, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

6 open issues indexed

🐛[BUG]: Directly constructed model wrappers silently run force autograd with create_graph=True (train-mode default) Open

bug

NVIDIA/nvalchemi-toolkit#173 · 1 assignee · Opened Aug 18, 2026
Feature request: sampler-less compaction / per-graph early-exit for BaseDynamics.run() Open

NVIDIA/nvalchemi-toolkit#172 · 1 assignee · Opened Aug 18, 2026
🚀[FEA]: Return up to Max Neighbors When Calculating Neighbor Lists Open

enhancement

Difficulty 4/5 3-5 days Newbie friendliness 45/100

NVIDIA/nvalchemi-toolkit#128 · Opened Jul 4, 2026
🐛[BUG]: Default derivative function set will include `positions` if `energies` is specified Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 75/100

NVIDIA/nvalchemi-toolkit#100 · Opened May 30, 2026
🐛[BUG]: Threshold is actually optional if using custom_op Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 55/100

NVIDIA/nvalchemi-toolkit#83 · 2 comments · Opened Apr 27, 2026
refactor(data): replace fragile regex in __inc__ and _get_cat_dim with explicit key sets Open

enhancement

Difficulty 3/5 1-2 days Newbie friendliness 72/100

NVIDIA/nvalchemi-toolkit#58 · Opened Apr 8, 2026

A short digest of beginner-friendly GitHub issues.