{"total":15,"rows":[{"id":"2411.00136","title":"LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators","created":"2024-10-31","cited_by_count":32,"area":null},{"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":"2408.14158","title":"Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning","created":"2024-08-26","cited_by_count":8,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2502.08145","title":"Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers","created":"2025-02-12","cited_by_count":7,"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":"2512.12131","title":"BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models","created":"2025-12-13","cited_by_count":2,"area":null},{"id":"2503.20191","title":"Maya: Optimizing Deep Learning Training Workloads using GPU Runtime Emulation","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2509.15741","title":"TrueMoE: Dual-Routing Mixture of Discriminative Experts for Synthetic Image Detection","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.15893","title":"Accelerating Frontier MoE Training with 3D Integrated Optics","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2512.10236","title":"Design Space Exploration of DMA based Finer-Grain Compute Communication Overlap","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2601.22585","title":"HetCCL: Accelerating LLM Training with Heterogeneous GPUs","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2504.18658","title":"The Big Send-off: Scalable and Performant Collectives for Deep Learning","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2509.26541","title":"TASP: Topology-aware Sequence Parallelism","created":"2025-09-30","cited_by_count":0,"area":null}],"next_cursor":null}