{"total":29,"rows":[{"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":"2312.14972","title":"Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production","created":"2023-12-20","cited_by_count":21,"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":"2305.14516","title":"Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces","created":"2023-05-23","cited_by_count":13,"area":null},{"id":"2407.14645","title":"Performance Modeling and Workload Analysis of Distributed Large Language Model Training and Inference","created":"2024-07-19","cited_by_count":9,"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":"2410.23261","title":"$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources","created":"2024-10-30","cited_by_count":6,"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":"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":"2401.16492","title":"GPU Cluster Scheduling for Network-Sensitive Deep Learning","created":"2024-01-29","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":"2606.28565","title":"KernelSight-LM: A Kernel-Level LLM Inference Simulator","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2503.01770","title":"m4: A Learned Flow-level Network Simulator","created":"2025-03-03","cited_by_count":1,"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":"2505.23523","title":"Efficient AllReduce with Stragglers","created":"2025-05-29","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":"2601.19107","title":"TinyTorch: Building Machine Learning Systems from First Principles","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2401.00329","title":"On the Burstiness of Distributed Machine Learning Traffic","created":"2023-12-30","cited_by_count":0,"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":"2603.06798","title":"NEST: Network- and Memory-Aware Device Placement For Distributed Deep Learning","created":"2026-03-06","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":"2605.17164","title":"Charon: A Unified and Fine-Grained Simulator for Large-Scale LLM Training and Inference","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.24006","title":"A Tabular Schedule Abstraction for Communication-Aware Evaluation of Pipeline-Parallel LLM Training","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.10440","title":"ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.02558","title":"MLSYSIM: First-Principles Infrastructure Modeling for Machine Learning Systems","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2608.15762","title":"Global Simulation-Guided Dynamic Operator Scheduling for Efficient Multi-Tenant Model Serving","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.19924","title":"The Life of a Token: from Words to Bits on the Wire","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}