hao-ai-lab/d3LLM

d3LLM: Ultra-Fast Diffusion LLM 🚀

31
/ 100
Emerging

This project helps AI practitioners develop and deploy specialized text generation models much faster. It takes existing large language models and refines them into 'diffusion LLMs' that generate text up to five times quicker, especially for tasks like coding and math. Anyone building or fine-tuning AI models for rapid text generation in specific domains would use this.

105 stars.

Use this if you need to generate text very quickly, particularly for coding or mathematical reasoning, using an AI model that maintains high accuracy.

Not ideal if your primary goal is general conversational AI or if you don't require significant speed improvements over standard autoregressive models.

AI model training natural language generation code generation mathematical reasoning AI model deployment
No License No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 5 / 25
Community 7 / 25

How are scores calculated?

Stars

105

Forks

4

Language

Python

License

Last pushed

Feb 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hao-ai-lab/d3LLM"

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