Xiaohao-Liu/Awesome-Multi-Token-Prediction

A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more.

32
/ 100
Emerging

This is a curated collection of cutting-edge research and resources focused on Multi-Token Prediction (MTP). MTP is a technique that enables language and multimodal AI models to predict several words or parts of words at once, making them faster and more powerful. This resource is for AI researchers, machine learning engineers, and developers who are exploring or implementing advanced language model architectures.

Use this if you are a researcher or engineer looking for the latest academic papers and implementations on optimizing large language models and speech-language models using multi-token prediction techniques.

Not ideal if you are an end-user simply wanting to apply an existing language model, rather than studying or developing its core architecture and efficiency.

AI-research language-model-optimization deep-learning-efficiency natural-language-processing speech-language-models
No License No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 7 / 25
Community 7 / 25

How are scores calculated?

Stars

54

Forks

3

Language

License

Last pushed

Feb 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Xiaohao-Liu/Awesome-Multi-Token-Prediction"

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