{"total":15,"rows":[{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660,"area":null},{"id":"2405.07719","title":"USP: A Unified Sequence Parallelism Approach for Long Context Generative AI","created":"2024-05-13","cited_by_count":61,"area":null},{"id":"2404.10933","title":"LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs","created":"2024-04-16","cited_by_count":12,"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":"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":"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":"2406.08334","title":"ProTrain: Efficient LLM Training via Memory-Aware Techniques","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2212.05339","title":"Elixir: Train a Large Language Model on a Small GPU Cluster","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2403.12317","title":"EffiPerception: an Efficient Framework for Various Perception Tasks","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2605.16184","title":"Runtime-Orchestrated Second-Order Optimization for Scalable LLM Training","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2405.18047","title":"2BP: 2-Stage Backpropagation","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2512.17570","title":"GreedySnake: Accelerating SSD-Offloaded LLM Training with Efficient Scheduling and Optimizer Step Overlapping","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2604.27085","title":"Efficient Training on Multiple Consumer GPUs with RoundPipe","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2608.15211","title":"TERRA: A Hierarchical Parallel Training and Memory Orchestration Framework for High-Resolution AI-based Earth Modeling","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.32177","title":"Federated 3D Gaussian Splatting for Large-Scale Scene Reconstruction at Wireless Edge","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}