{"total":22,"rows":[{"id":"2405.05465","title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","created":"2024-05-08","cited_by_count":117,"area":null},{"id":"2102.00527","title":"A Runtime-Based Computational Performance Predictor for Deep Neural Network Training","created":"2021-01-31","cited_by_count":29,"area":null},{"id":"2202.07896","title":"Aryl: An Elastic Cluster Scheduler for Deep Learning","created":"2022-02-16","cited_by_count":27,"area":null},{"id":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26,"area":null},{"id":"2312.12391","title":"vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training","created":"2023-11-27","cited_by_count":23,"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":"2205.02473","title":"dPRO: A Generic Profiling and Optimization System for Expediting Distributed DNN Training","created":"2022-05-05","cited_by_count":12,"area":null},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2201.07821","title":"Building a Performance Model for Deep Learning Recommendation Model Training on GPUs","created":"2022-01-19","cited_by_count":10,"area":null},{"id":"2504.11750","title":"Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures","created":"2025-04-16","cited_by_count":8,"area":null},{"id":"2102.02344","title":"Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models","created":"2021-02-03","cited_by_count":7,"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":"2301.04122","title":"Mystique: Enabling Accurate and Scalable Generation of Production AI Benchmarks","created":"2022-12-16","cited_by_count":5,"area":null},{"id":"2509.22832","title":"Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2309.07181","title":"The Grand Illusion: The Myth of Software Portability and Implications for ML Progress","created":"2023-09-12","cited_by_count":3,"area":null},{"id":"2603.23566","title":"AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization","created":"2026-03-24","cited_by_count":3,"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":"2412.12487","title":"Echo: Simulating Distributed Training At Scale","created":"2024-12-17","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":"2403.16125","title":"Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design","created":"2024-03-24","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":"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}],"next_cursor":null}