AIPython★ 1,394⑂ 181 forksMIT
Zefan-Cai/KVCache-Factory
KVCache-Factory: Cache Compression for LLM
Unified KV-cache compression methods for autoregressive models. Memory savings and faster inference in one package.
// KEY FEATURES
- Unified approach to KV-cache compression
- Support for autoregressive models
- Open-source Python implementation
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram