{"total":102,"rows":[{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196,"area":"inference"},{"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":"2407.12820","title":"PQCache: Product Quantization-based KVCache for Long Context LLM Inference","created":"2024-07-01","cited_by_count":95,"area":"inference"},{"id":"2312.05516","title":"Stateful Large Language Model Serving with Pensieve","created":"2023-12-09","cited_by_count":61,"area":"inference"},{"id":"2506.02634","title":"KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider","created":"2025-06-03","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":"2508.18572","title":"Strata: Hierarchical Context Caching for Long Context Language Model Serving","created":"2025-08-26","cited_by_count":26,"area":"inference"},{"id":"2505.07203","title":"PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications","created":"2025-05-12","cited_by_count":21,"area":"inference"},{"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":"2510.18586","title":"TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications","created":"2025-10-21","cited_by_count":16,"area":"inference"},{"id":"2411.17089","title":"KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation","created":"2024-11-26","cited_by_count":13,"area":"inference"},{"id":"2507.06608","title":"Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving","created":"2025-07-09","cited_by_count":13,"area":"inference"},{"id":"2511.01815","title":"KV Cache Transform Coding for Compact Storage in LLM Inference","created":"2025-11-03","cited_by_count":13,"area":"inference"},{"id":"2511.20172","title":"Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management","created":"2025-11-25","cited_by_count":11,"area":"inference"},{"id":"2604.15039","title":"Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter","created":"2026-04-16","cited_by_count":11,"area":"inference"},{"id":"2502.03589","title":"HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference","created":"2025-02-05","cited_by_count":10,"area":"inference"},{"id":"2506.11309","title":"SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding","created":"2025-06-12","cited_by_count":9,"area":"inference"},{"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":"2603.17435","title":"ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression","created":"2026-03-18","cited_by_count":8,"area":"inference"},{"id":"2604.03143","title":"TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing","created":"2026-04-03","cited_by_count":8,"area":"inference"},{"id":"2504.04704","title":"LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important","created":"2025-04-07","cited_by_count":7,"area":"inference"},{"id":"2509.00579","title":"KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV Cache","created":"2025-08-30","cited_by_count":7,"area":"inference"},{"id":"2605.13734","title":"KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving","created":"2026-05-13","cited_by_count":7,"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":"2508.01002","title":"Optimal Scheduling Algorithms for LLM Inference: Theory and Practice","created":"2025-08-01","cited_by_count":6,"area":"inference"},{"id":"2509.02121","title":"Batch Query Processing and Optimization for Agentic Workflows","created":"2025-09-02","cited_by_count":6,"area":"inference"},{"id":"2411.18424","title":"FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving","created":"2024-11-27","cited_by_count":5,"area":"inference"},{"id":"2502.15955","title":"Compression Barriers for Autoregressive Transformers","created":"2025-02-21","cited_by_count":5,"area":"inference"},{"id":"2506.08018","title":"KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache","created":"2025-05-18","cited_by_count":5,"area":"inference"},{"id":"2509.19228","title":"CompLLM: Compression for Long Context Q&A","created":"2025-09-23","cited_by_count":5,"area":"inference"},{"id":"2511.00868","title":"FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache Management","created":"2025-11-02","cited_by_count":5,"area":"inference"},{"id":"2511.11907","title":"KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference","created":"2025-11-14","cited_by_count":5,"area":"inference"},{"id":"2512.12284","title":"V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval","created":"2025-12-13","cited_by_count":5,"area":"inference"},{"id":"2602.18755","title":"DualScale: Energy-Efficient Disaggregated LLM Serving via Phase-Aware Placement and DVFS","created":"2026-02-21","cited_by_count":5,"area":"inference"},{"id":"2603.14224","title":"Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys","created":"2026-03-15","cited_by_count":5,"area":"inference"},{"id":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"id":"2504.20828","title":"Ascendra: Dynamic Request Prioritization for Efficient LLM Serving","created":"2025-04-29","cited_by_count":4,"area":"inference"},{"id":"2605.07068","title":"WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems","created":"2026-05-08","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":"2503.08461","title":"FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework","created":"2025-03-11","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":"2507.19823","title":"HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs","created":"2025-07-26","cited_by_count":3,"area":"inference"},{"id":"2509.16857","title":"ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching","created":"2025-09-21","cited_by_count":3,"area":"inference"},{"id":"2604.21335","title":"Sub-Token Routing for KV Cache Compression","created":"2026-04-23","cited_by_count":3,"area":"inference"},{"id":"2605.24022","title":"Adaptive KV Cache Reuse for Fast Long-Context LLM Serving","created":"2026-05-20","cited_by_count":3,"area":"inference"},{"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":"2408.04107","title":"FDC: Fast KV Dimensionality Compression for Efficient LLM Inference","created":"2024-08-07","cited_by_count":2,"area":"inference"},{"id":"2504.09775","title":"MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference","created":"2025-04-14","cited_by_count":2,"area":"inference"},{"id":"2505.16502","title":"Recursive Offloading for LLM Serving in Multi-tier Networks","created":"2025-05-22","cited_by_count":2,"area":"inference"},{"id":"2505.21919","title":"Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM Inference","created":"2025-05-28","cited_by_count":2,"area":"inference"},{"id":"2512.15705","title":"Dynamic Rebatching for Efficient Early-Exit Inference with DREX","created":"2025-12-17","cited_by_count":2,"area":"inference"},{"id":"2512.24449","title":"PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression","created":"2025-12-30","cited_by_count":2,"area":"inference"},{"id":"2601.08833","title":"Revisiting Disaggregated Large Language Model Serving for Performance and Energy Implications","created":"2025-11-14","cited_by_count":2,"area":"inference"},{"id":"2601.20309","title":"SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips","created":"2026-01-28","cited_by_count":2,"area":"inference"},{"id":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","cited_by_count":2,"area":"inference"},{"id":"2605.22884","title":"Tensor Cache: Eviction-conditioned Associative Memory for Transformers","created":"2026-05-21","cited_by_count":2,"area":"inference"},{"id":"2606.19746","title":"SAC: Disaggregated KV Cache System for Sparse Attention LLMs with CXL","created":"2026-06-18","cited_by_count":2,"area":"inference"},{"id":"2607.28150","title":"SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer","created":"2026-07-30","cited_by_count":2,"area":"inference"},{"id":"2609.07883","title":"Deadline-Aware Adaptive Prefill Chunking for Efficient Large Language Model Serving","created":"2026-09-07","cited_by_count":2,"area":"inference"},{"id":"2504.20101","title":"PlanetServe: A Decentralized, Scalable, and Privacy-Preserving Overlay for Democratizing Large Language Model Serving","created":"2025-04-27","cited_by_count":1,"area":"inference"},{"id":"2505.23970","title":"Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving","created":"2025-05-29","cited_by_count":1,"area":"inference"},{"id":"2512.00719","title":"SIMPLE: Disaggregating Sampling from GPU Inference into a Decision Plane for Faster Distributed LLM Serving","created":"2025-11-30","cited_by_count":1,"area":"inference"},{"id":"2601.03067","title":"Joint Encoding of KV-Cache Blocks for Scalable LLM Serving","created":"2026-01-06","cited_by_count":1,"area":"inference"},{"id":"2601.19910","title":"Understanding Bottlenecks for Efficiently Serving LLM Inference With KV Offloading","created":"2025-12-16","cited_by_count":1,"area":"inference"},{"id":"2602.09725","title":"Efficient Remote KV Cache Reuse with GPU-native Video Codec","created":"2026-02-10","cited_by_count":1,"area":"inference"},{"id":"2603.10726","title":"PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems","created":"2026-03-11","cited_by_count":1,"area":"inference"},{"id":"2603.17456","title":"Stage-Aware Communication Scheduling for Disaggregated LLM Serving","created":"2026-03-18","cited_by_count":1,"area":"inference"},{"id":"2604.19769","title":"TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference","created":"2026-03-27","cited_by_count":1,"area":"inference"},{"id":"2604.21231","title":"SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference","created":"2026-04-23","cited_by_count":1,"area":"inference"},{"id":"2605.22850","title":"ObjectCache: Layerwise Object-Storage Retrieval for KV Cache Reuse","created":"2026-05-16","cited_by_count":1,"area":"inference"},{"id":"2606.03910","title":"NetKV: Network-Aware Decode Instance Selection for Disaggregated LLM Inference","created":"2026-06-02","cited_by_count":1,"area":"inference"},{"id":"2606.17787","title":"LUMEN: Coordinated Failure Recovery for Distributed LLM Serving","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2606.24033","title":"RoPE-Aware Bit Allocation for KV-Cache Quantization","created":"2026-06-23","cited_by_count":1,"area":"inference"},{"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":"2608.13263","title":"vToken: Token-Level Virtualization for Reclaimable KV Caches","created":"2026-08-13","cited_by_count":1,"area":"inference"},{"id":"2502.15804","title":"FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference","created":"2025-02-19","cited_by_count":0,"area":"inference"},{"id":"2510.25412","title":"Serve Programs, Not Prompts","created":"2025-10-29","cited_by_count":0,"area":"inference"},{"id":"2603.21257","title":"CALVO: Improve Serving Efficiency for LLM Inferences with Intense Network Demands","created":"2026-03-22","cited_by_count":0,"area":"inference"},{"id":"2605.09735","title":"KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving","created":"2026-05-10","cited_by_count":0,"area":"inference"},{"id":"2606.13708","title":"Tiara: A Programmable Line-Rate ISA for Remote Memory Access","created":"2026-06-10","cited_by_count":0,"area":"inference"},{"id":"2606.14779","title":"Unified KV Pooling to Accelerate Long-Context LLM Serving","created":"2026-06-10","cited_by_count":0,"area":"inference"},{"id":"2606.31093","title":"Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.02525","title":"PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving","created":"2026-05-10","cited_by_count":0,"area":"inference"},{"id":"2607.02574","title":"From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.05399","title":"Benchmarking KV-Cache Optimizations across Task Quality and System Performance for Long-Context Serving","created":"2026-05-03","cited_by_count":0,"area":"inference"},{"id":"2607.20538","title":"Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches","created":"2026-07-10","cited_by_count":0,"area":"inference"},{"id":"2608.06007","title":"TensorCast: The Missing Tensor Management Layer in Large Language Model Infrastructure","created":"2026-08-06","cited_by_count":0,"area":"inference"},{"id":"2608.10545","title":"ImpactHO: Importance-Aware KV Cache Transfer for Multi-User Edge LLM Handover","created":"2026-08-11","cited_by_count":0,"area":"inference"},{"id":"2608.16477","title":"Pallas: A Proactive KV Cache Migration Framework for LLM Inference in AI-RAN","created":"2026-08-17","cited_by_count":0,"area":"inference"},{"id":"2609.01338","title":"mzCache: On-Device LLM Memory Management under Multitasking","created":"2026-09-01","cited_by_count":0,"area":"inference"},{"id":"2609.06940","title":"Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.11744","title":"Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs","created":"2026-09-10","cited_by_count":0,"area":"inference"},{"id":"2609.19657","title":"PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving","created":"2026-09-17","cited_by_count":0,"area":"inference"},{"id":"2609.19880","title":"D-Quant: Driftable Entropy Coding for KV Cache Quantization","created":"2026-09-17","cited_by_count":0,"area":"inference"},{"id":"2609.25451","title":"Fast Recovery for LLM Serving via Decoupled Device Memory Lifetime in Dynamo","created":"2026-09-21","cited_by_count":0,"area":"inference"},{"id":"2609.30854","title":"The KV Cache Is the New Memory Wall","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.31415","title":"Evaluating the accuracy of KV cache reuse techniques","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.33536","title":"Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.35065","title":"TempoKV: Timely Staging of LLM KV Caches for Memory-Semantic Flash","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.39131","title":"Characterizing High Bandwidth Flash for LLM Serving","created":"2026-09-30","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}