cold-compress
PublicCold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.
Discover Popular AI-MCP Services - Find Your Perfect Match Instantly
Easy MCP Client Integration - Access Powerful AI Capabilities
Master MCP Usage - From Beginner to Expert
Top MCP Service Performance Rankings - Find Your Best Choice
Publish & Promote Your MCP Services
Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.