MLPerf: A Benchmark Suite for Machine Learning – Gu-Yeon Wei
summary
Presents MLPerf, a benchmark suite designed to evaluate machine learning systems. Describes the suite’s goals, the types of ML workloads and models it covers, and how MLPerf measures and compares performance across hardware and software implementations.
AI-written summary · about
related talks
39mMethodology of ML in Performance Testing (How to Find Bottlenecks Automatically)
19mApples, Oranges, and ML Models: Model Validation vs Benchmarking
29mEnhancing Performance Test Results with ML & LLMs: Communication Beyond the Numbers
06mML for Systems and Systems for ML
32mA Practical Guide To Benchmarking AI and GPU Workloads in Kubernetes
26mML Product Experiments at Scale
52mClassifying Performance Test Results Using Machine Learning
20mWell-Architecture Framework for Machine Learning