jagmarques/nexusquant

Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.

⭐ 25 ⑂ 1 Python NOASSERTION · 18 天前推送

attention compression inference llama llm llm-inference mistral pytorch quantization transformers vllm kv-cache long-context memory-efficient vector-quantization e8-lattice token-eviction

25

Watchers

0

贡献者

0

Commits

0

Releases

0

Open Issues

18 天前

最近推送

原文中文

暂无 README