Awesome-LLM-KV-Cache and Awesome-KV-Cache-Management

These are **competitors**, as both projects aim to be a curated list of research papers and code links related to KV cache optimization in LLMs, requiring users to choose one over the other for their primary resource.

Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 13/25
Maintenance 6/25
Adoption 10/25
Maturity 8/25
Community 9/25
Stars: 417
Forks: 26
Downloads:
Commits (30d): 0
Language:
License: GPL-3.0
Stars: 291
Forks: 9
Downloads:
Commits (30d): 0
Language:
License:
Stale 6m No Package No Dependents
No License No Package No Dependents

About Awesome-LLM-KV-Cache

Zefan-Cai/Awesome-LLM-KV-Cache

Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.

This is a curated list of research papers and associated codebases focused on optimizing the Key-Value (KV) cache in large language models (LLMs). It helps AI researchers and practitioners stay up-to-date with the latest advancements in LLM inference efficiency. You get a categorized list of academic papers, often with links to their code, and insight into different strategies for managing KV caches.

AI-research LLM-inference model-optimization deep-learning-efficiency natural-language-processing

About Awesome-KV-Cache-Management

TreeAI-Lab/Awesome-KV-Cache-Management

This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding code links.

This project is for developers who work with Large Language Models (LLMs) and need to improve their performance, particularly regarding memory usage and speed. It collects and categorizes research papers on "KV Cache Management," which is a technique to optimize how LLMs process information. The output is a curated list of research papers and their code, helping developers find methods to make their LLMs run faster and more efficiently.

Large Language Models LLM development AI model optimization AI research Machine Learning engineering

Scores updated daily from GitHub, PyPI, and npm data. How scores work