{"total":95,"rows":[{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235,"area":"inference"},{"id":"2410.21465","title":"ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference","created":"2024-10-28","cited_by_count":134,"area":"inference"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2510.09665","title":"LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference","created":"2025-10-08","cited_by_count":126,"area":"inference"},{"id":"2502.20766","title":"FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference","created":"2025-02-28","cited_by_count":123,"area":null},{"id":"2409.10516","title":"RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2408.11049","title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding","created":"2024-08-20","cited_by_count":91,"area":"inference"},{"id":"2411.09688","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","created":"2024-11-14","cited_by_count":57,"area":null},{"id":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2502.14866","title":"LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention","created":"2025-02-20","cited_by_count":41,"area":"inference"},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2602.02958","title":"Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization","created":"2026-02-03","cited_by_count":23,"area":"diffusion"},{"id":"2412.10543","title":"METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation","created":"2024-12-13","cited_by_count":17,"area":"rag"},{"id":"2504.19720","title":"Taming the Titans: A Survey of Efficient LLM Inference Serving","created":"2025-04-28","cited_by_count":16,"area":"inference"},{"id":"2510.04265","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","created":"2025-10-05","cited_by_count":15,"area":"lr"},{"id":"2506.13059","title":"Multipole Attention for Efficient Long Context Reasoning","created":"2025-06-16","cited_by_count":14,"area":"lr"},{"id":"2505.02922","title":"RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference","created":"2025-05-05","cited_by_count":13,"area":"inference"},{"id":"2508.06447","title":"SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning","created":"2025-08-08","cited_by_count":13,"area":"inference"},{"id":"2508.06297","title":"KV Cache Compression for Inference Efficiency in LLMs: A Review","created":"2025-08-08","cited_by_count":12,"area":"inference"},{"id":"2502.00527","title":"PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration","created":"2025-02-01","cited_by_count":10,"area":"inference"},{"id":"2512.01278","title":"Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding","created":"2025-12-01","cited_by_count":10,"area":"lr"},{"id":"2602.08005","title":"ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference","created":"2026-02-08","cited_by_count":9,"area":"inference"},{"id":"2503.24000","title":"Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving","created":"2025-03-31","cited_by_count":8,"area":"inference"},{"id":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"id":"2602.06502","title":"DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving","created":"2026-02-06","cited_by_count":8,"area":"inference"},{"id":"2502.04077","title":"AttentionPredictor: Temporal Patterns Matter for KV Cache Compression","created":"2025-02-06","cited_by_count":7,"area":"inference"},{"id":"2502.12665","title":"A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization","created":"2025-02-18","cited_by_count":7,"area":"inference"},{"id":"2602.07223","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","created":"2026-02-06","cited_by_count":7,"area":"inference"},{"id":"2409.11057","title":"KVPruner: Structural Pruning for Faster and Memory-Efficient Large Language Models","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2502.15304","title":"SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention","created":"2025-02-21","cited_by_count":6,"area":"inference"},{"id":"2504.07494","title":"Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving","created":"2025-04-10","cited_by_count":6,"area":"inference"},{"id":"2508.02751","title":"SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference","created":"2025-08-03","cited_by_count":6,"area":"inference"},{"id":"2509.24832","title":"SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching","created":"2025-09-29","cited_by_count":6,"area":"inference"},{"id":"2510.05688","title":"vAttention: Verified Sparse Attention","created":"2025-10-07","cited_by_count":6,"area":null},{"id":"2502.06766","title":"Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2602.05191","title":"Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"id":"2604.10539","title":"IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs","created":"2026-04-12","cited_by_count":5,"area":"inference"},{"id":"2503.11132","title":"X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression","created":"2025-03-14","cited_by_count":4,"area":"inference"},{"id":"2510.11292","title":"LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences","created":"2025-10-13","cited_by_count":4,"area":"inference"},{"id":"2511.00321","title":"Scalable Processing-Near-Memory for 1M-Token LLM Inference: CXL-Enabled KV-Cache Management Beyond GPU Limits","created":"2025-10-31","cited_by_count":4,"area":"inference"},{"id":"2512.17452","title":"KV Admission: Learning What to Write for Efficient Long-Context LLM Inference","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2605.20868","title":"Runtime-Certified Bounded-Error Quantized Attention","created":"2026-05-20","cited_by_count":4,"area":"inference"},{"id":"2607.08057","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","created":"2026-07-09","cited_by_count":4,"area":"inference"},{"id":"2412.05896","title":"XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference","created":"2024-12-08","cited_by_count":3,"area":"inference"},{"id":"2504.10326","title":"AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference","created":"2025-04-14","cited_by_count":3,"area":"inference"},{"id":"2505.24179","title":"SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2506.19505","title":"AnTKV: Anchor Token-Aware Sub-Bit Vector Quantization for KV Cache in Large Language Models","created":"2025-06-24","cited_by_count":3,"area":"inference"},{"id":"2601.03043","title":"Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage","created":"2026-01-06","cited_by_count":3,"area":null},{"id":"2602.06283","title":"SOCKET: SOft Collision Kernel EsTimator for Sparse Attention","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2606.02964","title":"Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving","created":"2026-06-01","cited_by_count":3,"area":"inference"},{"id":"2606.05875","title":"QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving","created":"2026-06-04","cited_by_count":3,"area":"rag"},{"id":"2608.07009","title":"HiSparse: Scaling Sparse-Attention Decoding with Hierarchical KV Cache Management","created":"2026-08-07","cited_by_count":3,"area":"inference"},{"id":"2507.13681","title":"LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues","created":"2025-07-18","cited_by_count":2,"area":"inference"},{"id":"2511.14510","title":"LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference","created":"2025-11-18","cited_by_count":2,"area":"inference"},{"id":"2602.03295","title":"POP: Prefill-Only Pruning for Efficient Large Model Inference","created":"2026-02-03","cited_by_count":2,"area":"mllm"},{"id":"2602.07721","title":"ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs","created":"2026-02-07","cited_by_count":2,"area":"inference"},{"id":"2602.11958","title":"RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2603.29494","title":"VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2604.08584","title":"CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference","created":"2026-03-30","cited_by_count":2,"area":"inference"},{"id":"2604.18137","title":"AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2605.11864","title":"Very Efficient Listwise Multimodal Reranking for Long Documents","created":"2026-05-12","cited_by_count":2,"area":"rag"},{"id":"2606.31519","title":"RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference","created":"2026-06-30","cited_by_count":2,"area":"inference"},{"id":"2607.11976","title":"LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2609.13141","title":"SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking","created":"2026-09-11","cited_by_count":2,"area":null},{"id":"2409.17527","title":"Data Proportion Detection for Optimized Data Management for Large Language Models","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2506.15704","title":"Learn from the Past: Fast Sparse Indexing for Large Language Model Decoding","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2601.13631","title":"ContiguousKV: Accelerating LLM Prefill with Granularity-Aligned KV Cache Management","created":"2026-01-20","cited_by_count":1,"area":"inference"},{"id":"2602.03922","title":"Online Vector Quantized Attention","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.10353","title":"S-HPLB: Efficient LLM Attention Serving via Sparsity-Aware Head Parallelism Load Balance","created":"2026-03-11","cited_by_count":1,"area":"inference"},{"id":"2603.18446","title":"UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.08426","title":"KV Cache Offloading for Context-Intensive Tasks","created":"2026-04-09","cited_by_count":1,"area":"inference"},{"id":"2605.06763","title":"Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache","created":"2026-05-07","cited_by_count":1,"area":"inference"},{"id":"2605.07234","title":"Reformulating KV Cache Eviction Problem for Long-Context LLM Inference","created":"2026-05-08","cited_by_count":1,"area":"inference"},{"id":"2607.24148","title":"A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference","created":"2026-07-27","cited_by_count":1,"area":"vla"},{"id":"2607.24555","title":"LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.09412","title":"KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models","created":"2026-08-10","cited_by_count":1,"area":"inference"},{"id":"2410.23805","title":"UpANNS: Enhancing Billion-Scale ANNS Efficiency with Real-World PIM Architecture","created":"2024-10-31","cited_by_count":0,"area":"rag"},{"id":"2602.03184","title":"DynSplit-KV: Dynamic Semantic Splitting for KVCache Compression in Efficient Long-Context LLM Inference","created":"2026-02-03","cited_by_count":0,"area":"inference"},{"id":"2603.20616","title":"Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression","created":"2026-03-21","cited_by_count":0,"area":"inference"},{"id":"2604.05012","title":"Comparative Characterization of KV Cache Management Strategies for LLM Inference","created":"2026-04-06","cited_by_count":0,"area":"inference"},{"id":"2604.24820","title":"Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.24168","title":"Inference Time Context Sparsity: Illusion or Opportunity?","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.21448","title":"Fast-TurboQuant: A Multiplier-Free Online Vector Quantization Approach","created":"2026-06-19","cited_by_count":0,"area":"inference"},{"id":"2608.07855","title":"CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents","created":"2026-08-08","cited_by_count":0,"area":"inference"},{"id":"2608.12780","title":"SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention","created":"2026-08-13","cited_by_count":0,"area":"diffusion"},{"id":"2609.13205","title":"Self-Indexing Attention for Compression-Compatible Sparse Long-Context LLM Inference","created":"2026-08-16","cited_by_count":0,"area":"inference"},{"id":"2609.33746","title":"PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34555","title":"PulseInfer: I/O-Centric Sparse KV Cache Offloading for Efficient Long-Context LLM Decoding","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2610.11458","title":"Generative Adversarial Loops","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14688","title":"Accelerating Cross-Model LLM Inference via Attention Map Reuse","created":"2026-10-10","cited_by_count":0,"area":"inference"},{"id":"2610.15324","title":"TempoKV: Predictive KV Cache Quantization for Autoregressive Video Generation","created":"2026-10-11","cited_by_count":0,"area":"diffusion"},{"id":"2610.15384","title":"E8 Lattice Key Quantization for Low-Bit KV-Cache Compression","created":"2026-10-11","cited_by_count":0,"area":"inference"}],"next_cursor":null}