GitHub · Python
xcena-dev/maru
High-Performance KV Cache Storage Engine on CXL Shared Memory for LLM Inference
- Stars
- 67
- Forks
- 6
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: cxl, kv-cache, llm, lmcache, python, shared-memory, vllm, zero-copy
Latest data point: Nov 21, 2026 · 67 stars · 6 forks