{"total":637,"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":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2510.04618","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","created":"2025-10-06","cited_by_count":398,"area":"agents"},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"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":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"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":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"area":null},{"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":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"area":null},{"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":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"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":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125,"area":null},{"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":"2403.09636","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","created":"2024-03-14","cited_by_count":116,"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":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"area":"lr"},{"id":"2506.06122","title":"Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library","created":"2025-06-06","cited_by_count":101,"area":"lr"},{"id":"2406.18139","title":"LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference","created":"2024-06-26","cited_by_count":95,"area":"mllm"},{"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":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77,"area":null},{"id":"2505.21467","title":"FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion","created":"2025-05-27","cited_by_count":77,"area":"diffusion"},{"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":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"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":"2405.18137","title":"Exploiting LLM Quantization","created":"2024-05-28","cited_by_count":65,"area":null},{"id":"2412.03213","title":"ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression","created":"2024-12-04","cited_by_count":65,"area":"lr"},{"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":"2411.09688","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","created":"2024-11-14","cited_by_count":57,"area":null},{"id":"2503.18278","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","created":"2025-03-24","cited_by_count":57,"area":"mllm"},{"id":"2505.24133","title":"R-KV: Redundancy-aware KV Cache Compression for Reasoning Models","created":"2025-05-30","cited_by_count":54,"area":"lr"},{"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":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46,"area":null},{"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":"2408.07092","title":"Post-Training Sparse Attention with Double Sparsity","created":"2024-08-11","cited_by_count":45,"area":null},{"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":"2405.08944","title":"Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis","created":"2024-05-14","cited_by_count":44,"area":"agents"},{"id":"2410.08584","title":"ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification","created":"2024-10-11","cited_by_count":44,"area":"mllm"},{"id":"2410.23317","title":"VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration","created":"2024-10-29","cited_by_count":43,"area":"mllm"},{"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":"2505.09343","title":"Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures","created":"2025-05-14","cited_by_count":39,"area":"moe"},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2502.06975","title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","created":"2025-02-10","cited_by_count":36,"area":"agents"},{"id":"2406.12016","title":"Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization","created":"2024-06-17","cited_by_count":33,"area":null},{"id":"2407.04965","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2410.05004","title":"Fast State Restoration in LLM Serving with HCache","created":"2024-10-07","cited_by_count":33,"area":"rag"},{"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":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"area":null},{"id":"2502.17599","title":"MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference","created":"2025-02-24","cited_by_count":31,"area":"mllm"},{"id":"2505.05799","title":"MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design","created":"2025-05-09","cited_by_count":30,"area":"moe"},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2506.18879","title":"CommVQ: Commutative Vector Quantization for KV Cache Compression","created":"2025-06-23","cited_by_count":28,"area":"inference"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2410.01518","title":"InfiniPot: Infinite Context Processing on Memory-Constrained LLMs","created":"2024-10-02","cited_by_count":27,"area":null},{"id":"2502.10424","title":"QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache","created":"2025-02-05","cited_by_count":27,"area":"inference"},{"id":"2502.14837","title":"Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs","created":"2025-02-20","cited_by_count":27,"area":"lr"},{"id":"2506.05345","title":"Inference-Time Hyper-Scaling with KV Cache Compression","created":"2025-06-05","cited_by_count":27,"area":"lr"},{"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":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26,"area":null},{"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":"2504.11651","title":"70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)","created":"2025-04-15","cited_by_count":24,"area":"diffusion"},{"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":"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":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22,"area":null},{"id":"2505.18610","title":"PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs","created":"2025-05-24","cited_by_count":22,"area":"lr"},{"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":"2510.01290","title":"ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models","created":"2025-10-01","cited_by_count":21,"area":"lr"},{"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":"2505.22038","title":"Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization","created":"2025-05-28","cited_by_count":20,"area":"mllm"},{"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":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2411.17691","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","created":"2024-11-26","cited_by_count":18,"area":null},{"id":"2505.10938","title":"Accurate KV Cache Quantization with Outlier Tokens Tracing","created":"2025-05-16","cited_by_count":18,"area":"inference"}],"next_cursor":"100"}