{"total":59,"rows":[{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853,"area":null},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660,"area":null},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2205.05198","title":"Reducing Activation Recomputation in Large Transformer Models","created":"2022-05-10","cited_by_count":302,"area":null},{"id":"2405.05465","title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","created":"2024-05-08","cited_by_count":117,"area":null},{"id":"2105.04663","title":"GSPMD: General and Scalable Parallelization for ML Computation Graphs","created":"2021-05-10","cited_by_count":111,"area":null},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87,"area":null},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46,"area":null},{"id":"2404.07947","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","created":"2024-03-15","cited_by_count":45,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2412.19823","title":"A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions","created":"2024-12-16","cited_by_count":25,"area":null},{"id":"2201.12023","title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning","created":"2022-01-28","cited_by_count":20,"area":null},{"id":"2211.05322","title":"On Optimizing the Communication of Model Parallelism","created":"2022-11-10","cited_by_count":19,"area":null},{"id":"2111.05897","title":"Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2503.17924","title":"WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training","created":"2025-03-23","cited_by_count":17,"area":null},{"id":"2108.05818","title":"PatrickStar: Parallel Training of Pre-trained Models via Chunk-based Memory Management","created":"2021-08-12","cited_by_count":15,"area":null},{"id":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","cited_by_count":13,"area":null},{"id":"2110.14895","title":"Pipeline Parallelism for Inference on Heterogeneous Edge Computing","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2210.07297","title":"AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2301.02654","title":"Does compressing activations help model parallel training?","created":"2023-01-06","cited_by_count":12,"area":null},{"id":"2501.01124","title":"Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning","created":"2025-01-02","cited_by_count":12,"area":null},{"id":"2111.05972","title":"Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training","created":"2021-11-10","cited_by_count":11,"area":null},{"id":"2208.10921","title":"AI and 6G into the Metaverse: Fundamentals, Challenges and Future Research Trends","created":"2022-08-23","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":"2411.00284","title":"SimpleFSDP: Simpler Fully Sharded Data Parallel with torch.compile","created":"2024-11-01","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":"2504.14519","title":"SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training","created":"2025-04-20","cited_by_count":6,"area":null},{"id":"2112.02752","title":"End-to-end Adaptive Distributed Training on PaddlePaddle","created":"2021-12-06","cited_by_count":5,"area":null},{"id":"2301.08984","title":"SuperScaler: Supporting Flexible DNN Parallelization via a Unified Abstraction","created":"2023-01-21","cited_by_count":5,"area":null},{"id":"2302.02599","title":"Colossal-Auto: Unified Automation of Parallelization and Activation Checkpoint for Large-scale Models","created":"2023-02-06","cited_by_count":5,"area":null},{"id":"2503.01328","title":"PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2301.02691","title":"Systems for Parallel and Distributed Large-Model Deep Learning Training","created":"2023-01-06","cited_by_count":4,"area":null},{"id":"2501.14784","title":"DeServe: Towards Affordable Offline LLM Inference via Decentralization","created":"2025-01-04","cited_by_count":4,"area":null},{"id":"2202.07138","title":"Integrating AI Planning with Natural Language Processing: A Combination of Explicit and Tacit Knowledge","created":"2022-02-15","cited_by_count":3,"area":null},{"id":"2302.00247","title":"TAPAS: Fast and Automatic Derivation of Tensor Parallel Strategies for Large Neural Networks","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2308.08500","title":"InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models","created":"2023-08-13","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":"2301.08695","title":"Baechi: Fast Device Placement of Machine Learning Graphs","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2302.08141","title":"Auto-Parallelizing Large Models with Rhino: A Systematic Approach on Production AI Platform","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2309.01226","title":"Saturn: An Optimized Data System for Large Model Deep Learning Workloads","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2409.02423","title":"Accelerating Large Language Model Training with Hybrid GPU-based Compression","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2411.06465","title":"Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimator","created":"2024-11-10","cited_by_count":2,"area":null},{"id":"2507.00394","title":"HelixPipe: Efficient Distributed Training of Long Sequence Transformers with Attention Parallel Pipeline Parallelism","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2601.09026","title":"Layer-Parallel Training for Transformers","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2206.01733","title":"Adversarial RAW: Image-Scaling Attack Against Imaging Pipeline","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2301.03386","title":"Need of 6G for the Metaverse Realization","created":"2022-12-28","cited_by_count":0,"area":null},{"id":"2311.02840","title":"Saturn: Efficient Multi-Large-Model Deep Learning","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2311.03703","title":"Practical Performance Guarantees for Pipelined DNN Inference","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2402.09589","title":"MLCC: A Congestion Control Technique to Accelerate ML Training","created":"2024-02-14","cited_by_count":0,"area":null},{"id":"2403.16125","title":"Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2410.08791","title":"Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models","created":"2024-10-11","cited_by_count":0,"area":null},{"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":"2509.21275","title":"Concertina: Data-Centric Adaptive Pipeline Parallelism for Efficient Heterogeneous Long-Context LLM Training","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2602.02632","title":"Performance of Small Language Model Pretraining on FABRIC: An Empirical Study","created":"2026-02-02","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":"2609.35263","title":"WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.14935","title":"BSIPipe: Bidirectional Sequence-Level Interleaved Pipeline Parallelism for Long-Sequence Large Language Model Training","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}