{"total":191,"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":"2403.02310","title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve","created":"2024-03-04","cited_by_count":526,"area":"inference"},{"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":"2308.16369","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills","created":"2023-08-31","cited_by_count":193,"area":"inference"},{"id":"2406.03243","title":"Llumnix: Dynamic Scheduling for Large Language Model Serving","created":"2024-06-05","cited_by_count":174,"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":"2305.05920","title":"Fast Distributed Inference Serving for Large Language Models","created":"2023-05-10","cited_by_count":145,"area":"inference"},{"id":"2405.19888","title":"Parrot: Efficient Serving of LLM-based Applications with Semantic Variable","created":"2024-05-30","cited_by_count":99,"area":null},{"id":"2311.15566","title":"SpotServe: Serving Generative Large Language Models on Preemptible Instances","created":"2023-11-27","cited_by_count":87,"area":"inference"},{"id":"2310.18547","title":"Punica: Multi-Tenant LoRA Serving","created":"2023-10-28","cited_by_count":83,"area":null},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82,"area":null},{"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":"2105.01984","title":"Software Engineering for AI-Based Systems: A Survey","created":"2021-05-05","cited_by_count":69,"area":null},{"id":"2312.05516","title":"Stateful Large Language Model Serving with Pensieve","created":"2023-12-09","cited_by_count":61,"area":"inference"},{"id":"2404.02015","title":"MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving","created":"2024-04-02","cited_by_count":52,"area":"inference"},{"id":"2407.00047","title":"Queue management for slo-oriented large language model serving","created":"2024-06-05","cited_by_count":36,"area":"inference"},{"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":"2201.07705","title":"GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge","created":"2022-01-19","cited_by_count":32,"area":null},{"id":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32,"area":null},{"id":"2202.07896","title":"Aryl: An Elastic Cluster Scheduler for Deep Learning","created":"2022-02-16","cited_by_count":27,"area":null},{"id":"2205.10162","title":"FedAdapter: Efficient Federated Learning for Modern NLP","created":"2022-05-20","cited_by_count":25,"area":null},{"id":"2209.09125","title":"Operationalizing Machine Learning: An Interview Study","created":"2022-09-16","cited_by_count":25,"area":null},{"id":"2107.01739","title":"KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks","created":"2021-07-04","cited_by_count":20,"area":null},{"id":"2210.08803","title":"Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference","created":"2022-10-17","cited_by_count":20,"area":null},{"id":"2408.05235","title":"SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving","created":"2024-08-05","cited_by_count":19,"area":"inference"},{"id":"2312.05215","title":"DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs","created":"2023-12-08","cited_by_count":18,"area":null},{"id":"2212.00972","title":"Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-world","created":"2022-12-02","cited_by_count":17,"area":"distill"},{"id":"2510.08439","title":"xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning","created":"2025-10-09","cited_by_count":17,"area":null},{"id":"2206.00136","title":"End-to-end Optimization of Machine Learning Prediction Queries","created":"2022-05-31","cited_by_count":16,"area":null},{"id":"2311.16136","title":"ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach","created":"2023-11-03","cited_by_count":15,"area":"safety"},{"id":"2312.05385","title":"Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving","created":"2023-12-08","cited_by_count":15,"area":"inference"},{"id":"2210.11831","title":"Management of Machine Learning Lifecycle Artifacts: A Survey","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2403.00793","title":"Ads Recommendation in a Collapsed and Entangled World","created":"2024-02-22","cited_by_count":13,"area":null},{"id":"2403.12900","title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2205.04713","title":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures","created":"2022-05-10","cited_by_count":12,"area":null},{"id":"2312.16733","title":"SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads","created":"2023-12-27","cited_by_count":12,"area":null},{"id":"2206.06304","title":"Multi-user Co-inference with Batch Processing Capable Edge Server","created":"2022-06-03","cited_by_count":11,"area":null},{"id":"2305.10863","title":"Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness","created":"2023-05-18","cited_by_count":11,"area":null},{"id":"2312.16279","title":"Cloud-Device Collaborative Learning for Multimodal Large Language Models","created":"2023-12-26","cited_by_count":11,"area":"lr"},{"id":"2402.17316","title":"Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation","created":"2024-02-27","cited_by_count":11,"area":null},{"id":"2405.06856","title":"Aladdin: Joint Placement and Scaling for SLO-Aware LLM Serving","created":"2024-05-11","cited_by_count":11,"area":"inference"},{"id":"2404.06114","title":"Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey","created":"2024-04-09","cited_by_count":10,"area":null},{"id":"2407.07000","title":"Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems","created":"2024-07-09","cited_by_count":10,"area":"inference"},{"id":"2102.03012","title":"A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning","created":"2021-02-05","cited_by_count":9,"area":null},{"id":"2106.03122","title":"ModelCI-e: Enabling Continual Learning in Deep Learning Serving Systems","created":"2021-06-06","cited_by_count":9,"area":null},{"id":"2210.08804","title":"A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2402.18789","title":"FlexLLM: Token-Level Co-Serving of LLM Inference and Finetuning with SLO Guarantees","created":"2024-02-29","cited_by_count":9,"area":null},{"id":"2504.15465","title":"LithOS: An Operating System for Efficient Machine Learning on GPUs","created":"2025-04-21","cited_by_count":9,"area":null},{"id":"2505.09142","title":"ELIS: Efficient LLM Iterative Scheduling System with Response Length Predictor","created":"2025-05-14","cited_by_count":9,"area":"inference"},{"id":"2101.07344","title":"Accelerating Deep Learning Inference via Learned Caches","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2110.10305","title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models","created":"2021-10-19","cited_by_count":8,"area":null},{"id":"2504.10724","title":"HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving","created":"2025-04-14","cited_by_count":8,"area":"inference"},{"id":"2109.03947","title":"SensiX++: Bringing MLOPs and Multi-tenant Model Serving to Sensory Edge Devices","created":"2021-09-08","cited_by_count":7,"area":null},{"id":"2109.11067","title":"Serving DNN Models with Multi-Instance GPUs: A Case of the Reconfigurable Machine Scheduling Problem","created":"2021-09-18","cited_by_count":7,"area":null},{"id":"2206.02845","title":"On Efficient Approximate Queries over Machine Learning Models","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2304.02101","title":"MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2508.00234","title":"Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts","created":"2025-08-01","cited_by_count":7,"area":null},{"id":"2105.01803","title":"DeepRT: A Soft Real Time Scheduler for Computer Vision Applications on the Edge","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2205.11913","title":"Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Vision","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2209.13443","title":"Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs","created":"2022-09-27","cited_by_count":6,"area":"inference"},{"id":"2405.00790","title":"SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators","created":"2024-05-01","cited_by_count":6,"area":null},{"id":"2105.11738","title":"FENXI: Deep-learning Traffic Analytics at the Edge","created":"2021-05-25","cited_by_count":5,"area":null},{"id":"2109.09868","title":"ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems","created":"2021-09-20","cited_by_count":5,"area":null},{"id":"2304.10892","title":"Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems","created":"2023-04-21","cited_by_count":5,"area":null},{"id":"2310.18481","title":"MOSEL: Inference Serving Using Dynamic Modality Selection","created":"2023-10-27","cited_by_count":5,"area":null},{"id":"2310.19991","title":"PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2312.04429","title":"Approximate Caching for Efficiently Serving Diffusion Models","created":"2023-12-07","cited_by_count":5,"area":"diffusion"},{"id":"2402.03480","title":"Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2405.00568","title":"Powering In-Database Dynamic Model Slicing for Structured Data Analytics","created":"2024-05-01","cited_by_count":5,"area":"moe"},{"id":"2405.03924","title":"NeurDB: An AI-powered Autonomous Data System","created":"2024-05-07","cited_by_count":5,"area":null},{"id":"2407.02031","title":"SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules","created":"2024-07-02","cited_by_count":5,"area":"diffusion"},{"id":"2410.01228","title":"ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2109.01611","title":"Multi-model Machine Learning Inference Serving with GPU Spatial Partitioning","created":"2021-09-01","cited_by_count":4,"area":null},{"id":"2301.12865","title":"SMDP-Based Dynamic Batching for Efficient Inference on GPU-Based Platforms","created":"2023-01-30","cited_by_count":4,"area":null},{"id":"2406.14424","title":"CascadeServe: Unlocking Model Cascades for Inference Serving","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2410.17840","title":"Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs","created":"2024-10-23","cited_by_count":4,"area":null},{"id":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2601.19402","title":"PROTEUS: SLA-Aware Routing via Lagrangian RL for Multi-LLM Serving Systems","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2103.02958","title":"Serverless Data Science -- Are We There Yet? A Case Study of Model Serving","created":"2021-03-04","cited_by_count":3,"area":null},{"id":"2210.05889","title":"KAIROS: Building Cost-Efficient Machine Learning Inference Systems with Heterogeneous Cloud Resources","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2302.04430","title":"A Comparison of Decision Forest Inference Platforms from A Database Perspective","created":"2023-02-09","cited_by_count":3,"area":null},{"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":"2105.08275","title":"ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2107.00957","title":"Ascent Similarity Caching with Approximate Indexes","created":"2021-07-02","cited_by_count":2,"area":null},{"id":"2112.06671","title":"Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching","created":"2021-12-13","cited_by_count":2,"area":null},{"id":"2210.04323","title":"Deep Learning Inference Frameworks Benchmark","created":"2022-10-09","cited_by_count":2,"area":null},{"id":"2305.01519","title":"BCEdge: SLO-Aware DNN Inference Services with Adaptive Batching on Edge Platforms","created":"2023-05-01","cited_by_count":2,"area":null},{"id":"2307.01292","title":"Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems","created":"2023-07-03","cited_by_count":2,"area":null},{"id":"2307.01684","title":"Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Services","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2308.07470","title":"Symphony: Optimized DNN Model Serving using Deferred Batch Scheduling","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2308.12871","title":"IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency","created":"2023-08-24","cited_by_count":2,"area":null},{"id":"2310.04696","title":"Serving Deep Learning Model in Relational Databases","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2311.18174","title":"Packrat: Automatic Reconfiguration for Latency Minimization in CPU-based DNN Serving","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2405.11191","title":"Biathlon: Harnessing Model Resilience for Accelerating ML Inference Pipelines","created":"2024-05-18","cited_by_count":2,"area":null},{"id":"2411.10337","title":"On the Cost of Model-Serving Frameworks: An Experimental Evaluation","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2505.07680","title":"SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models","created":"2025-05-12","cited_by_count":2,"area":"inference"},{"id":"2106.05345","title":"Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud","created":"2021-06-09","cited_by_count":1,"area":null},{"id":"2107.06131","title":"Identification of Dynamical Systems using Symbolic Regression","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2107.13821","title":"Concept for a Technical Infrastructure for Management of Predictive Models in Industrial Applications","created":"2021-07-29","cited_by_count":1,"area":null},{"id":"2202.11243","title":"MLProxy: SLA-Aware Reverse Proxy for Machine Learning Inference Serving on Serverless Computing Platforms","created":"2022-02-23","cited_by_count":1,"area":null}],"next_cursor":"100"}