AIPython★ 1,223⑂ 197 forksApache-2.0
Zefan-Cai/R-KV
R-KV: Compress KV-Cache 1200+ Stars
NeurIPS 2025: smart KV-cache compression for reasoning models accounting for redundancy. Faster, less memory, same accuracy.
// KEY FEATURES
- NeurIPS 2025, 1203 ⭐
- Redundancy-aware KV-cache compression
- Optimization for reasoning models
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram