ReKV: Overlapping Quantized KV Transfer and Suffix Recomputation
cs.DC
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Splitwise: Efficient generative LLM inference using phase splitting
- SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving
- CacheFlow: Efficient LLM Serving with 3D-Parallel KV Cache Restoration
- Qwen2.5 Technical Report
- The Llama 3 Herd of Models
- Pointer Sentinel Mixture Models
- Qwen3 Technical Report
- Training Verifiers to Solve Math Word Problems
- MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool
- P/D-Serve: Serving Disaggregated Large Language Model at Scale
- KVDirect: Distributed Disaggregated LLM Inference
- LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management
- KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
- HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
- SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer
Related papers
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends
- AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition