July 23, 2026 HyMCache: A KV Cache Framework for Multi-Turn LLM Serving with CXL-Hybrid Memory Cost-Efficient Remote KV-Cache Tier Using CXL-Hybrid Memory for Scalable LLM Serving kv-cache llm-serving cxl-memory memory-tiering multi-turn-llm disaggregated-inference remote-caching
July 23, 2026 HyMCache A KV Cache Framework for Multi-Turn LLM Serving with CXL-Hybrid Memory llm-serving kv-cache cxl-memory memory-tiering remote-caching pd-disaggregation rdma