pengzhangzhi/Open-dLLM

Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.

50
/ 100
Established

Open-dLLM provides a complete open-source toolkit for diffusion-based large language models, specifically for code generation. It takes a prompt or partial code as input and generates runnable code or fills in missing code. This project is for machine learning researchers and developers who want to experiment with, train, and evaluate diffusion models for programming tasks.

549 stars.

Use this if you are a machine learning researcher or developer interested in the full lifecycle of building, evaluating, and deploying diffusion-based models for code generation, including accessing the pretraining pipeline and checkpoints.

Not ideal if you are looking for a pre-built, production-ready code generation API or a tool for casual programming assistance without diving into model training and evaluation.

code-generation diffusion-models machine-learning-research model-training code-completion
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

549

Forks

42

Language

Python

License

Apache-2.0

Last pushed

Mar 01, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/pengzhangzhi/Open-dLLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.