{"total":53,"rows":[{"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":"2311.15566","title":"SpotServe: Serving Generative Large Language Models on Preemptible Instances","created":"2023-11-27","cited_by_count":87,"area":"inference"},{"id":"2504.15930","title":"StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation","created":"2025-04-22","cited_by_count":61,"area":null},{"id":"2304.03946","title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement","created":"2023-04-08","cited_by_count":53,"area":"moe"},{"id":"2409.13221","title":"Optimizing RLHF Training for Large Language Models with Stage Fusion","created":"2024-09-20","cited_by_count":43,"area":"alignment"},{"id":"2312.15159","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","created":"2023-12-23","cited_by_count":33,"area":null},{"id":"2404.14527","title":"M\\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity","created":"2024-04-22","cited_by_count":31,"area":null},{"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":"2412.01523","title":"FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism","created":"2024-12-02","cited_by_count":19,"area":null},{"id":"2309.10285","title":"Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity","created":"2023-09-19","cited_by_count":17,"area":null},{"id":"2307.02031","title":"Improving Automatic Parallel Training via Balanced Memory Workload Optimization","created":"2023-07-05","cited_by_count":14,"area":null},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"area":null},{"id":"2406.13511","title":"Slice-Level Scheduling for High Throughput and Load Balanced LLM Serving","created":"2024-06-19","cited_by_count":13,"area":"inference"},{"id":"2509.26182","title":"Parallax: Efficient LLM Inference Service over Decentralized Environment","created":"2025-09-30","cited_by_count":12,"area":"inference"},{"id":"2401.02643","title":"Training and Serving System of Foundation Models: A Comprehensive Survey","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2511.00796","title":"AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs","created":"2025-11-02","cited_by_count":9,"area":null},{"id":"2601.06288","title":"AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving","created":"2026-01-09","cited_by_count":9,"area":"inference"},{"id":"2303.02868","title":"Angel-PTM: A Scalable and Economical Large-scale Pre-training System in Tencent","created":"2023-03-06","cited_by_count":8,"area":null},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2409.03365","title":"Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling","created":"2024-09-05","cited_by_count":7,"area":null},{"id":"2503.19050","title":"Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization","created":"2025-03-24","cited_by_count":7,"area":null},{"id":"2504.09307","title":"Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training","created":"2025-04-12","cited_by_count":7,"area":null},{"id":"2504.07494","title":"Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving","created":"2025-04-10","cited_by_count":6,"area":"inference"},{"id":"2602.10729","title":"BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization","created":"2026-02-11","cited_by_count":6,"area":"inference"},{"id":"2602.11686","title":"LAER-MoE: Load-Adaptive Expert Re-layout for Efficient Mixture-of-Experts Training","created":"2026-02-12","cited_by_count":6,"area":"moe"},{"id":"2404.09022","title":"Navigating the Landscape of Large Language Models: A Comprehensive Review and Analysis of Paradigms and Fine-Tuning Strategies","created":"2024-04-13","cited_by_count":5,"area":null},{"id":"2407.12117","title":"MEMO: Fine-grained Tensor Management For Ultra-long Context LLM Training","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2506.04203","title":"Cascadia: An Efficient Cascade Serving System for Large Language Models","created":"2025-06-04","cited_by_count":5,"area":"inference"},{"id":"2406.08334","title":"ProTrain: Efficient LLM Training via Memory-Aware Techniques","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2606.03077","title":"Libra: Efficient Resource Management for Agentic RL Post-Training","created":"2026-06-02","cited_by_count":4,"area":"agents"},{"id":"2412.07894","title":"Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment","created":"2024-12-10","cited_by_count":3,"area":null},{"id":"2510.00206","title":"LoRAFusion: Efficient LoRA Fine-Tuning for LLMs","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2602.12151","title":"OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration","created":"2026-02-12","cited_by_count":3,"area":"inference"},{"id":"2307.16375","title":"UniAP: Unifying Inter- and Intra-Layer Automatic Parallelism by Mixed Integer Quadratic Programming","created":"2023-07-31","cited_by_count":2,"area":null},{"id":"2509.23722","title":"OctoPipe: Reducing Pipeline Bubbles for Heterogeneous Models via Co-Optimizing Partitioning, Placement, and Scheduling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2605.28302","title":"How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving","created":"2026-05-27","cited_by_count":2,"area":"moe"},{"id":"2501.13111","title":"iServe: An Intent-based Serving System for LLMs","created":"2025-01-08","cited_by_count":1,"area":"inference"},{"id":"2603.11603","title":"AutoScout: Structured Optimization for Automating ML System Configuration","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.07144","title":"Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics","created":"2026-04-08","cited_by_count":1,"area":"inference"},{"id":"2604.19654","title":"FEPLB: Exploiting Copy Engines for Nearly Free MoE Load Balancing in Distributed Training","created":"2026-04-21","cited_by_count":1,"area":"moe"},{"id":"2607.18631","title":"Searching for Plans You Can Actually Build: A Realizability-Aware Full-Space Optimizer for MoE Training and Serving","created":"2026-07-21","cited_by_count":1,"area":"moe"},{"id":"2503.09357","title":"Automatic Operator-level Parallelism Planning for Distributed Deep Learning -- A Mixed-Integer Programming Approach","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2504.21411","title":"Galvatron: An Automatic Distributed System for Efficient Foundation Model Training","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2506.02787","title":"Rethinking Dynamic Networks and Heterogeneous Computing with Automatic Parallelization","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2507.11506","title":"ELK: Exploring the Efficiency of Inter-core Connected AI Chips with Deep Learning Compiler Techniques","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2601.02311","title":"Placement Semantics for Distributed Deep Learning: A Systematic Framework for Analyzing Parallelism Strategies","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2605.16637","title":"HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling","created":"2026-05-15","cited_by_count":0,"area":"inference"},{"id":"2606.23087","title":"FlowTrain: Flow-Based Decoupled Training for Industrial-Grade Vision-Language Models","created":"2026-06-22","cited_by_count":0,"area":"mllm"},{"id":"2609.07236","title":"Parallelism Strategy Chaining for Fast Training Convergence","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.19924","title":"The Life of a Token: from Words to Bits on the Wire","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.39350","title":"HAPMoE: Heterogeneity-Aware Automatic Parallelism Planning for Mixture-of-Experts Models Training","created":"2026-09-30","cited_by_count":0,"area":"moe"},{"id":"2610.17528","title":"ATTUNE: Agentic Throughput Tuning for LLM Training","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19423","title":"Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}