xcena-dev/maru

High-Performance KV Cache Storage Engine on CXL Shared Memory for LLM Inference

⭐ 58 ⑂ 5 Python Apache-2.0 · 2 天前推送

https://xcena-dev.github.io/maru/

llm python vllm kv-cache cxl lmcache shared-memory zero-copy

58

Watchers

0

贡献者

0

Commits

0

Releases

14

Open Issues

2 天前

最近推送

原文中文

暂无 README