Unified KV Cache Compression Methods for Auto-Regressive Models
FasterKv.Cache is an in-process hybrid cache library (memory+disk) based on the Microsoft FasterKv.
LLM KV cache compression made easy
This is the implementation of CacheKV described in our paper "Redesigning High-Performance LSM-based Key-Value Stores with Persistent CPU Caches" appeared in IEEE ICDE'23.
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
Nachos OS, KV store, distributed KV Store
Cloudflare workers KV 图床
Vercel Postgres, KV, Blob, and Edge Config
Doctrine Cache component
翻译 - 原则缓存组件
A RocksDB compatible KV storage engine with better performance
翻译 - 与RocksDB兼容的KV存储引擎，性能更高
this is raft java project. raft-kv-storage
A Blog Powered By Cloudflare Workers and KV
翻译 - 由Cloudflare Workers和KV支持的博客
A geo-distributed KV store for metadata management
Golang 实现的LRU缓存
📦 Nothing but Cache.
a node internal (in-memory) caching module
A distributed KV store for Erlang and Elixir.