{"total":591,"rows":[{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135,"area":"moe"},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637,"area":"inference"},{"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":"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":"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":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"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":"2505.15781","title":"dKV-Cache: The Cache for Diffusion Language Models","created":"2025-05-21","cited_by_count":143,"area":"diffusion"},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"area":"rag"},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"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":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"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":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125,"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":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"area":"lr"},{"id":"2404.11912","title":"TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding","created":"2024-04-18","cited_by_count":102,"area":"inference"},{"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":"2407.15891","title":"RazorAttention: Efficient KV Cache Compression Through Retrieval Heads","created":"2024-07-22","cited_by_count":100,"area":"inference"},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2407.08454","title":"Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks","created":"2024-07-11","cited_by_count":96,"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":"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":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"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":"2510.00636","title":"Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution","created":"2025-10-01","cited_by_count":74,"area":"inference"},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73,"area":"lr"},{"id":"2408.05646","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","created":"2024-08-10","cited_by_count":72,"area":"lr"},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2402.04236","title":"CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning","created":"2024-02-06","cited_by_count":67,"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":"2411.09688","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","created":"2024-11-14","cited_by_count":57,"area":null},{"id":"2408.14690","title":"Training-Free Activation Sparsity in Large Language Models","created":"2024-08-26","cited_by_count":55,"area":"inference"},{"id":"2403.01241","title":"IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact","created":"2024-03-02","cited_by_count":52,"area":null},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52,"area":null},{"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":"2503.12559","title":"AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding","created":"2025-03-16","cited_by_count":48,"area":"mllm"},{"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":"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":"2410.08584","title":"ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification","created":"2024-10-11","cited_by_count":44,"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":"2412.14838","title":"DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs","created":"2024-12-19","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":"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":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"area":null},{"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":"2502.15734","title":"Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation","created":"2025-02-05","cited_by_count":36,"area":"rag"},{"id":"2410.05004","title":"Fast State Restoration in LLM Serving with HCache","created":"2024-10-07","cited_by_count":33,"area":"rag"},{"id":"2412.20504","title":"ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding","created":"2024-12-29","cited_by_count":33,"area":"inference"},{"id":"2502.06415","title":"Systematic Outliers in Large Language Models","created":"2025-02-10","cited_by_count":33,"area":null},{"id":"2403.12766","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens","created":"2024-03-18","cited_by_count":32,"area":null},{"id":"2408.05499","title":"LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale","created":"2024-08-10","cited_by_count":31,"area":"inference"},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"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":"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":"2605.18739","title":"LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation","created":"2026-05-18","cited_by_count":30,"area":"diffusion"},{"id":"2410.14731","title":"MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection","created":"2024-10-16","cited_by_count":29,"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":"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":"2506.05345","title":"Inference-Time Hyper-Scaling with KV Cache Compression","created":"2025-06-05","cited_by_count":27,"area":"lr"},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2411.01783","title":"Context Parallelism for Scalable Million-Token Inference","created":"2024-11-04","cited_by_count":26,"area":null},{"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":"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":"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":"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":"2503.00353","title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","created":"2025-03-01","cited_by_count":20,"area":"rag"},{"id":"2410.03960","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","created":"2024-10-04","cited_by_count":19,"area":"inference"},{"id":"2502.07115","title":"Online Scheduling for LLM Inference with KV Cache Constraints","created":"2025-02-10","cited_by_count":19,"area":"inference"},{"id":"2504.08719","title":"SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling","created":"2025-04-11","cited_by_count":19,"area":null},{"id":"2504.11320","title":"Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints","created":"2025-04-15","cited_by_count":19,"area":null},{"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":"2410.11305","title":"QSpec: Speculative Decoding with Complementary Quantization Schemes","created":"2024-10-15","cited_by_count":18,"area":"inference"},{"id":"2410.13461","title":"Progressive Mixed-Precision Decoding for Efficient LLM Inference","created":"2024-10-17","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":"2508.04664","title":"Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management","created":"2025-08-06","cited_by_count":18,"area":null},{"id":"2403.20041","title":"Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs","created":"2024-03-29","cited_by_count":17,"area":null},{"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"}],"next_cursor":"100"}