{"total":349,"rows":[{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634,"area":"inference"},{"id":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288,"area":"inference"},{"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":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223,"area":"inference"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196,"area":"inference"},{"id":"2403.05527","title":"GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM","created":"2024-03-08","cited_by_count":158,"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":"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":"2505.23416","title":"KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction","created":"2025-05-29","cited_by_count":95,"area":"inference"},{"id":"2405.14256","title":"ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification","created":"2024-05-23","cited_by_count":93,"area":"inference"},{"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":"2405.03917","title":"KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization","created":"2024-05-07","cited_by_count":76,"area":"inference"},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66,"area":"inference"},{"id":"2407.21118","title":"Palu: Compressing KV-Cache with Low-Rank Projection","created":"2024-07-30","cited_by_count":64,"area":"inference"},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2502.00299","title":"ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference","created":"2025-02-01","cited_by_count":60,"area":"inference"},{"id":"2503.12491","title":"CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences","created":"2025-03-16","cited_by_count":58,"area":"inference"},{"id":"2406.03482","title":"QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead","created":"2024-06-05","cited_by_count":52,"area":"inference"},{"id":"2504.15364","title":"KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments","created":"2025-04-21","cited_by_count":51,"area":"inference"},{"id":"2501.16383","title":"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations","created":"2025-01-25","cited_by_count":46,"area":"inference"},{"id":"2405.06219","title":"SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models","created":"2024-05-10","cited_by_count":44,"area":"inference"},{"id":"2407.01527","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","created":"2024-07-01","cited_by_count":42,"area":"inference"},{"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":"2411.02886","title":"TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection","created":"2024-11-05","cited_by_count":39,"area":"inference"},{"id":"2406.13035","title":"D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models","created":"2024-06-18","cited_by_count":31,"area":"inference"},{"id":"2506.18879","title":"CommVQ: Commutative Vector Quantization for KV Cache Compression","created":"2025-06-23","cited_by_count":28,"area":"inference"},{"id":"2502.10424","title":"QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache","created":"2025-02-05","cited_by_count":27,"area":"inference"},{"id":"2412.03131","title":"DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV Compaction","created":"2024-12-04","cited_by_count":26,"area":"inference"},{"id":"2502.03805","title":"CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective","created":"2025-02-06","cited_by_count":26,"area":"inference"},{"id":"2410.03065","title":"Compute Or Load KV Cache? Why Not Both?","created":"2024-10-04","cited_by_count":25,"area":"inference"},{"id":"2411.17116","title":"Star Attention: Efficient LLM Inference over Long Sequences","created":"2024-11-26","cited_by_count":25,"area":"inference"},{"id":"2501.19392","title":"Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models","created":"2025-01-31","cited_by_count":24,"area":"inference"},{"id":"2502.09334","title":"ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments","created":"2025-02-13","cited_by_count":23,"area":"inference"},{"id":"2505.19602","title":"Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression","created":"2025-05-26","cited_by_count":22,"area":"inference"},{"id":"2504.19449","title":"R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference","created":"2025-04-28","cited_by_count":21,"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":"2412.13649","title":"SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation","created":"2024-12-18","cited_by_count":20,"area":"inference"},{"id":"2410.13212","title":"AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations","created":"2024-10-17","cited_by_count":19,"area":"inference"},{"id":"2512.03324","title":"Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs","created":"2025-12-03","cited_by_count":19,"area":"inference"},{"id":"2407.08892","title":"Characterizing Prompt Compression Methods for Long Context Inference","created":"2024-07-11","cited_by_count":18,"area":"inference"},{"id":"2505.10938","title":"Accurate KV Cache Quantization with Outlier Tokens Tracing","created":"2025-05-16","cited_by_count":18,"area":"inference"},{"id":"2412.08890","title":"Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries","created":"2024-12-12","cited_by_count":17,"area":"inference"},{"id":"2412.17483","title":"A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression","created":"2024-12-23","cited_by_count":17,"area":"inference"},{"id":"2507.08143","title":"Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores","created":"2025-07-10","cited_by_count":17,"area":"inference"},{"id":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"id":"2410.00428","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","created":"2024-10-01","cited_by_count":16,"area":"inference"},{"id":"2503.18893","title":"xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction","created":"2025-03-24","cited_by_count":16,"area":"inference"},{"id":"2505.24357","title":"ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration","created":"2025-05-30","cited_by_count":16,"area":"inference"},{"id":"2601.17668","title":"Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction","created":"2026-01-25","cited_by_count":16,"area":"inference"},{"id":"2410.01805","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","created":"2024-10-02","cited_by_count":15,"area":"inference"},{"id":"2410.03090","title":"UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective","created":"2024-10-04","cited_by_count":15,"area":"inference"},{"id":"2504.09261","title":"Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling","created":"2025-04-12","cited_by_count":15,"area":"inference"},{"id":"2601.07891","title":"KVzap: Fast, Adaptive, and Faithful KV Cache Pruning","created":"2026-01-12","cited_by_count":15,"area":"inference"},{"id":"2502.01068","title":"FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration","created":"2025-02-03","cited_by_count":14,"area":"inference"},{"id":"2503.18599","title":"Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization","created":"2025-03-24","cited_by_count":14,"area":"inference"},{"id":"2505.20334","title":"Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query","created":"2025-05-24","cited_by_count":14,"area":"inference"},{"id":"2510.13334","title":"Taming the Fragility of KV Cache Eviction in LLM Inference","created":"2025-10-15","cited_by_count":14,"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":"2412.18934","title":"Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference","created":"2024-12-25","cited_by_count":13,"area":"inference"},{"id":"2503.16257","title":"Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models","created":"2025-03-20","cited_by_count":13,"area":"inference"},{"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":"2511.01815","title":"KV Cache Transform Coding for Compact Storage in LLM Inference","created":"2025-11-03","cited_by_count":13,"area":"inference"},{"id":"2503.07518","title":"TokenButler: Token Importance is Predictable","created":"2025-03-10","cited_by_count":12,"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":"2411.05787","title":"RefreshKV: Updating Small KV Cache During Long-form Generation","created":"2024-11-08","cited_by_count":11,"area":"inference"},{"id":"2501.01144","title":"BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference","created":"2025-01-02","cited_by_count":11,"area":"inference"},{"id":"2510.24273","title":"SALS: Sparse Attention in Latent Space for KV cache Compression","created":"2025-10-28","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":"2605.09649","title":"Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction","created":"2026-05-10","cited_by_count":11,"area":"inference"},{"id":"2606.08382","title":"STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control","created":"2026-06-07","cited_by_count":11,"area":"inference"},{"id":"2412.12706","title":"More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression","created":"2024-12-17","cited_by_count":10,"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":"2502.15075","title":"Quantize What Counts: More for Keys, Less for Values","created":"2025-02-20","cited_by_count":10,"area":"inference"},{"id":"2505.19586","title":"TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization","created":"2025-05-26","cited_by_count":10,"area":"inference"},{"id":"2508.15601","title":"LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind","created":"2025-08-21","cited_by_count":10,"area":"inference"},{"id":"2510.02758","title":"TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling","created":"2025-10-03","cited_by_count":10,"area":"inference"},{"id":"2510.05373","title":"KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction","created":"2025-10-06","cited_by_count":10,"area":"inference"},{"id":"2511.18643","title":"Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost","created":"2025-11-23","cited_by_count":10,"area":"inference"},{"id":"2512.14946","title":"EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving","created":"2025-12-16","cited_by_count":10,"area":"inference"},{"id":"2410.22118","title":"The Impact of Inference Acceleration on Bias of LLMs","created":"2024-10-29","cited_by_count":9,"area":"inference"},{"id":"2411.15982","title":"Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"id":"2502.12574","title":"HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading","created":"2025-02-18","cited_by_count":9,"area":"inference"},{"id":"2503.16163","title":"SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs","created":"2025-03-20","cited_by_count":9,"area":"inference"},{"id":"2507.06517","title":"SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers","created":"2025-07-09","cited_by_count":9,"area":"inference"},{"id":"2508.02401","title":"CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation","created":"2025-08-04","cited_by_count":9,"area":"inference"},{"id":"2509.15763","title":"UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression","created":"2025-09-19","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":"2605.08840","title":"ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing","created":"2026-05-09","cited_by_count":9,"area":"inference"},{"id":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2501.06709","title":"Mell: Memory-Efficient Large Language Model Serving via Multi-GPU KV Cache Management","created":"2025-01-12","cited_by_count":8,"area":"inference"},{"id":"2501.14743","title":"KVDirect: Distributed Disaggregated LLM Inference","created":"2024-12-13","cited_by_count":8,"area":"inference"},{"id":"2503.18773","title":"BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache","created":"2025-03-24","cited_by_count":8,"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":"2506.11418","title":"CentroidKV: Efficient Long-Context LLM Inference via KV Cache Clustering","created":"2025-06-13","cited_by_count":8,"area":"inference"},{"id":"2512.11920","title":"CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving","created":"2025-12-11","cited_by_count":8,"area":"inference"},{"id":"2602.03152","title":"FASA: Frequency-aware Sparse Attention","created":"2026-02-03","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"}],"next_cursor":"100"}