Geralt-Targaryen/Awesome-Speculative-Decoding

Reading notes on Speculative Decoding papers

25
/ 100
Experimental

This is a curated reading list for researchers and practitioners focused on accelerating Large Language Model (LLM) inference. It compiles academic papers on 'speculative decoding' techniques from top AI conferences. The project organizes research by venue and specific method, providing direct links to papers for those exploring state-of-the-art LLM optimization.

Use this if you are an AI researcher or machine learning engineer looking to understand and apply cutting-edge methods for making large language models respond faster.

Not ideal if you are looking for an off-the-shelf tool or library to implement speculative decoding, or if you are not deeply involved in LLM research and development.

AI Research Large Language Models LLM Optimization Natural Language Processing Deep Learning Inference
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

25

Forks

—

Language

—

License

—

Category

speculative-decoding-algorithms

Last pushed

Feb 24, 2026

Commits (30d)

0

GitHub
Speculative Decoding Algorithms · 4 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Geralt-Targaryen/Awesome-Speculative-Decoding"

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

Higher-rated alternatives

vitali87/speculant-graph

Graph drafts, LLM verifies: a novel speculative decoding framework

35

hsj576/GRIFFIN

Official Implementation of "GRIFFIN: Effective Token Alignment for Faster Speculative...

33

Hambaobao/HCP-Coder

Hierarchical Context Pruning (HCP): A strategy to optimize real-world code completion with...

31

Explore LLM Tools

All categories Trending LLM Tool directory Insights