{"total":24,"rows":[{"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":"2104.12369","title":"PanGu-$\\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","created":"2021-04-26","cited_by_count":134,"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":"2104.05158","title":"Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models","created":"2021-04-12","cited_by_count":78,"area":null},{"id":"2209.10797","title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation","created":"2022-09-22","cited_by_count":48,"area":null},{"id":"2109.15082","title":"Towards Efficient Post-training Quantization of Pre-trained Language Models","created":"2021-09-30","cited_by_count":39,"area":null},{"id":"2103.00686","title":"Accelerating Recommendation System Training by Leveraging Popular Choices","created":"2021-03-01","cited_by_count":22,"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":"2210.02023","title":"DreamShard: Generalizable Embedding Table Placement for Recommender Systems","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2503.22567","title":"Benchmarking Ultra-Low-Power $\\mu$NPUs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2305.01868","title":"Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2509.10371","title":"Characterizing the Efficiency of Distributed Training: A Power, Performance, and Thermal Perspective","created":"2025-09-12","cited_by_count":5,"area":null},{"id":"2308.00890","title":"Tango: rethinking quantization for graph neural network training on GPUs","created":"2023-08-02","cited_by_count":4,"area":null},{"id":"2407.13143","title":"Integrated Hardware Architecture and Device Placement Search","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2111.00655","title":"Collage: Seamless Integration of Deep Learning Backends with Automatic Placement","created":"2021-11-01","cited_by_count":2,"area":null},{"id":"2111.05426","title":"DistIR: An Intermediate Representation and Simulator for Efficient Neural Network Distribution","created":"2021-11-09","cited_by_count":2,"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":"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":"2406.08756","title":"Optimizing Large Model Training through Overlapped Activation Recomputation","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2312.04025","title":"Moirai: Towards Optimal Placement for Distributed Inference on Heterogeneous Devices","created":"2023-12-07","cited_by_count":1,"area":null},{"id":"2509.19855","title":"CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2503.05324","title":"Routing for Large ML Models","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2603.06798","title":"NEST: Network- and Memory-Aware Device Placement For Distributed Deep Learning","created":"2026-03-06","cited_by_count":0,"area":null}],"next_cursor":null}