TempoKV: Timely Staging of LLM KV Caches for Memory-Semantic Flash

arXiv:2609.35065 · cs.DC, cs.AI, cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.DC, cs.AI, cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• KV cache — 1× in this paper · explained in 3 episodes

Sources

• The Llama 3 Herd of Models
• ITME: Inference Tiered Memory Expansion with Disaggregated CXL-Hybrid Memories
• A CXL Memory Rack for Multi-Turn LLM Serving
• LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
• PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving
• Qwen2.5 Technical Report
• TraCT: Disaggregated LLM Serving with CXL Shared Memory KV Cache at Rack-Scale

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence
• Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
• Democratizing MoE inference on commodity GPUs with CoMoE