CacheWeave: Learning to Recompute for Efficient Position-Independent KV Caching
cs.DC, cs.LG
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
- Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
- KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
- ATTUNER: Recomputation-Free Agentic Context KV Reuse
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- Gemma 4 Technical Report
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation
- LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
- RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention
- TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
- Block-Attention for Efficient Prefilling
- RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse
- Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
- InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- 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