{"total":23,"rows":[{"id":"2304.01433","title":"TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings","created":"2023-04-04","cited_by_count":202,"area":null},{"id":"2308.00852","title":"CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters","created":"2023-08-01","cited_by_count":26,"area":null},{"id":"2302.08545","title":"THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression","created":"2023-02-16","cited_by_count":15,"area":null},{"id":"2407.13853","title":"Forecasting GPU Performance for Deep Learning Training and Inference","created":"2024-07-18","cited_by_count":15,"area":null},{"id":"2310.02784","title":"MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systems","created":"2023-10-04","cited_by_count":14,"area":null},{"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":"2401.09356","title":"Swing: Short-cutting Rings for Higher Bandwidth Allreduce","created":"2024-01-17","cited_by_count":8,"area":null},{"id":"2502.03885","title":"InfiniteHBD: Building Datacenter-Scale High-Bandwidth Domain for LLM with Optical Circuit Switching Transceivers","created":"2025-02-06","cited_by_count":7,"area":null},{"id":"2202.03356","title":"Efficient Direct-Connect Topologies for Collective Communications","created":"2022-02-07","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":"2304.05301","title":"TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Machine Learning","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2312.03549","title":"Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2403.07585","title":"Communication Optimization for Distributed Training: Architecture, Advances, and Opportunities","created":"2024-03-12","cited_by_count":3,"area":null},{"id":"2504.20854","title":"Towards Easy and Realistic Network Infrastructure Testing for Large-scale Machine Learning","created":"2025-04-29","cited_by_count":3,"area":null},{"id":"2402.06787","title":"ForestColl: Throughput-Optimal Collective Communications on Heterogeneous Network Fabrics","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2401.02801","title":"Credence: Augmenting Datacenter Switch Buffer Sharing with ML Predictions","created":"2024-01-05","cited_by_count":1,"area":null},{"id":"2505.23523","title":"Efficient AllReduce with Stragglers","created":"2025-05-29","cited_by_count":1,"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":"2407.00467","title":"VcLLM: Video Codecs are Secretly Tensor Codecs","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2503.05324","title":"Routing for Large ML Models","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2505.23105","title":"LUMION: Fast Fault Recovery for ML Jobs Using Programmable Optical Fabrics","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2508.03674","title":"Morphlux: Transforming Torus Fabrics for Efficient Multi-tenant ML","created":"2025-07-20","cited_by_count":0,"area":null},{"id":"2510.19322","title":"Enabling Reconfiguration-Communication Overlap for Collective Communication in Optical Networks","created":"2025-10-22","cited_by_count":0,"area":null}],"next_cursor":null}