FastGen

★ 44 Open GitHub ↗

This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Explore Similar Repositories

SL2.1A-Type-C-Hub : A simple 4-port USB2 hub based on the SL2.1A design.
video-master : Auto Download Video From Social Media & Edit Video Fastest Easyly
HGINet-torch : Official code: Semantic change detection using a hierarchical semantic graph interaction network from high-resolution remote sensing images
mjml4j : Java implementation for MJML - a framework that makes responsive-email easy
Th3-GPT : Th3-GPT Prompt/Script Will Jailbreak ChatGPT / Other AI Models
// repository documentation