hao-ai-lab/JacobiForcing
Jacobi Forcing: Fast and Accurate Diffusion-style Decoding
This project helps anyone working with Large Language Models (LLMs) who needs faster text generation. It takes an existing LLM, trains it with a new technique called Jacobi Forcing, and outputs a significantly quicker model. The end user is typically a developer or researcher deploying or fine-tuning LLMs for applications where speed is critical, such as chatbots or coding assistants.
143 stars.
Use this if you want to accelerate the text generation speed of your causal LLMs, especially for tasks like coding or mathematics, without sacrificing output quality.
Not ideal if you are not working with LLMs or if you prioritize maximum generation quality over speed improvements.
Stars
143
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hao-ai-lab/JacobiForcing"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sgl-project/SpecForge
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
structuredllm/syncode
Efficient and general syntactical decoding for Large Language Models
SafeAILab/EAGLE
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
romsto/Speculative-Decoding
Implementation of the paper Fast Inference from Transformers via Speculative Decoding, Leviathan...
kssteven418/BigLittleDecoder
[NeurIPS'23] Speculative Decoding with Big Little Decoder