{"total":575,"rows":[{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944,"area":"inference"},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298,"area":null},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141,"area":null},{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"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":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617,"area":"inference"},{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591,"area":"inference"},{"id":"2403.02310","title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve","created":"2024-03-04","cited_by_count":526,"area":"inference"},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474,"area":"inference"},{"id":"2305.17118","title":"Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time","created":"2023-05-26","cited_by_count":439,"area":"inference"},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2305.09781","title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification","created":"2023-05-16","cited_by_count":365,"area":"inference"},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324,"area":null},{"id":"2310.19102","title":"Atom: Low-bit Quantization for Efficient and Accurate LLM Serving","created":"2023-10-29","cited_by_count":272,"area":"inference"},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268,"area":null},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2312.11970","title":"Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives","created":"2023-12-19","cited_by_count":257,"area":"agents"},{"id":"2406.19707","title":"InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management","created":"2024-06-28","cited_by_count":245,"area":"inference"},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"area":null},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"area":null},{"id":"2312.12456","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","created":"2023-12-16","cited_by_count":217,"area":null},{"id":"2305.16300","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","created":"2023-05-25","cited_by_count":213,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203,"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":"2308.16369","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills","created":"2023-08-31","cited_by_count":193,"area":"inference"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2312.11514","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","created":"2023-12-12","cited_by_count":177,"area":"inference"},{"id":"2403.19708","title":"Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention","created":"2024-03-23","cited_by_count":163,"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":"2311.03285","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","created":"2023-11-06","cited_by_count":152,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2308.04623","title":"Accelerating LLM Inference with Staged Speculative Decoding","created":"2023-08-08","cited_by_count":151,"area":"inference"},{"id":"2311.08252","title":"REST: Retrieval-Based Speculative Decoding","created":"2023-11-14","cited_by_count":150,"area":"inference"},{"id":"2405.12532","title":"PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference","created":"2024-05-21","cited_by_count":147,"area":"inference"},{"id":"2305.05920","title":"Fast Distributed Inference Serving for Large Language Models","created":"2023-05-10","cited_by_count":145,"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":"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":"2405.12981","title":"Reducing Transformer Key-Value Cache Size with Cross-Layer Attention","created":"2024-05-21","cited_by_count":131,"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":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"},{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2305.10427","title":"Accelerating Transformer Inference for Translation via Parallel Decoding","created":"2023-05-17","cited_by_count":124,"area":"inference"},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121,"area":null},{"id":"2312.04985","title":"SparQ Attention: Bandwidth-Efficient LLM Inference","created":"2023-12-08","cited_by_count":119,"area":"inference"},{"id":"2402.05109","title":"Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding","created":"2024-02-07","cited_by_count":117,"area":"inference"},{"id":"2304.01089","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","created":"2023-04-03","cited_by_count":116,"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":"2304.09433","title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes","created":"2023-04-19","cited_by_count":111,"area":null},{"id":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105,"area":"lr"},{"id":"2402.12374","title":"Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding","created":"2024-02-19","cited_by_count":103,"area":"inference"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"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":"2402.18096","title":"No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization","created":"2024-02-28","cited_by_count":101,"area":"inference"},{"id":"2407.15891","title":"RazorAttention: Efficient KV Cache Compression Through Retrieval Heads","created":"2024-07-22","cited_by_count":100,"area":"inference"},{"id":"2405.04437","title":"vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention","created":"2024-05-07","cited_by_count":98,"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":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2312.17238","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","created":"2023-12-28","cited_by_count":91,"area":"moe"},{"id":"2408.12757","title":"NanoFlow: Towards Optimal Large Language Model Serving Throughput","created":"2024-08-22","cited_by_count":90,"area":"inference"},{"id":"2311.15566","title":"SpotServe: Serving Generative Large Language Models on Preemptible Instances","created":"2023-11-27","cited_by_count":87,"area":"inference"},{"id":"2305.13144","title":"Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline","created":"2023-05-22","cited_by_count":86,"area":"inference"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2310.18547","title":"Punica: Multi-Tenant LoRA Serving","created":"2023-10-28","cited_by_count":83,"area":null},{"id":"2402.02834","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","created":"2024-02-05","cited_by_count":82,"area":null},{"id":"2402.15220","title":"ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition","created":"2024-02-23","cited_by_count":82,"area":"inference"},{"id":"2306.06000","title":"S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput","created":"2023-06-09","cited_by_count":81,"area":"inference"},{"id":"2401.14351","title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models","created":"2024-01-25","cited_by_count":80,"area":null},{"id":"2401.00588","title":"Fairness in Serving Large Language Models","created":"2023-12-31","cited_by_count":78,"area":"inference"},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77,"area":null},{"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":"2402.09398","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","created":"2024-02-14","cited_by_count":75,"area":"inference"},{"id":"2401.02669","title":"Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache","created":"2024-01-05","cited_by_count":73,"area":"inference"},{"id":"2402.05099","title":"Hydragen: High-Throughput LLM Inference with Shared Prefixes","created":"2024-02-07","cited_by_count":73,"area":null},{"id":"2411.11217","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs","created":"2024-11-18","cited_by_count":73,"area":"moe"},{"id":"2311.01282","title":"FlashDecoding++: Faster Large Language Model Inference on GPUs","created":"2023-11-02","cited_by_count":71,"area":"inference"},{"id":"2402.07033","title":"Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models","created":"2024-02-10","cited_by_count":71,"area":"moe"},{"id":"2406.17565","title":"MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool","created":"2024-06-25","cited_by_count":68,"area":"inference"},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67,"area":null},{"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":"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":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"area":null},{"id":"2312.05516","title":"Stateful Large Language Model Serving with Pensieve","created":"2023-12-09","cited_by_count":61,"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":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2405.10637","title":"Layer-Condensed KV Cache for Efficient Inference of Large Language Models","created":"2024-05-17","cited_by_count":59,"area":"inference"},{"id":"2502.13965","title":"Autellix: An Efficient Serving Engine for LLM Agents as General Programs","created":"2025-02-19","cited_by_count":58,"area":"agents"},{"id":"2404.02015","title":"MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving","created":"2024-04-02","cited_by_count":52,"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"}],"next_cursor":"100"}