Skip to main content
Context Awesome

awesome-llm-compression

github.com/huangowen/awesome-llm-compression ↗

Awesome LLM compression research papers and tools.

1.9k
GitHub Stars
1.2k
Curated Resources
2
Categories
21 hours ago
Last Refreshed
PapersTools

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me model compression toolkits resources from awesome-llm-compression"

Installation instructions →

What's inside

Tools

  • [Code]Model Compression Toolkits

  • [Code]Inference and Serving Engines

  • [Code]KV Cache and Prompt Compression

  • [Code]Inference and Serving Engines

  • [Code]Quantization Libraries and Kernels

  • [Code]Analysis and Benchmarking

Papers

Showing a sample of 1.2k resources. View the full list on GitHub →