benchmarks for measuring training and inference performance of ML hardware, software, and services
- AI is transforming multiple industries, but for it to reach its full potential, we still need faster hardware and software
- Good benchmarks enable researchers to compare different ideas quickly, which makes it easier to innovate.
- MLPerf can help people choose the right ML infrastructure for their applications
- MLPerf demonstrates the importance of innovating in scale-up computing as well as at all levels of the computing stack — from hardware architecture to software