{"total":14,"rows":[{"id":"2312.02515","title":"mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2504.09307","title":"Lumos: Efficient Performance Modeling and Estimation for Large-scale LLM Training","created":"2025-04-12","cited_by_count":7,"area":null},{"id":"2504.16397","title":"Compass: SLO-aware Query Planner for Compound AI Serving at Scale","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2504.17025","title":"Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2602.08564","title":"M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data","created":"2026-02-09","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":"2511.10480","title":"Scalable Synthesis of distributed LLM workloads through Symbolic Tensor Graphs","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2606.02430","title":"Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2405.02969","title":"Towards a Flexible and High-Fidelity Approach to Distributed DNN Training Emulation","created":"2024-05-05","cited_by_count":0,"area":null},{"id":"2505.01616","title":"Phantora: Maximizing Code Reuse in Simulation-based Machine Learning System Performance Estimation","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2507.14000","title":"Photonic Fabric Platform for AI Accelerators","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2604.16145","title":"Training Time Prediction for Mixed Precision-based Distributed Training","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.15617","title":"A Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with PrismLLM","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.07236","title":"Parallelism Strategy Chaining for Fast Training Convergence","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}