关于

GitHub 原始描述(英文)

Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality loss. Includes benchmarking, visualization, and one-command setup. Optimized for M1/M2/M3 Macs with Metal support.

描述取自 GitHub 官方 API,保持仓库作者书写的原文。

简要分析

热度分
393
价值分
221
活跃状态
活跃

语言占比

Python
Shell