Fostering a vibrant AI hardware accelerator ecosystem through enabling software technology.

We collaborate on the benchmarking, optimization, and adaptation of AI workloads to accelerate innovation in a diverse set of hardware. Our work focuses on scalability, platform adaptation, and advanced power, energy, and carbon modeling. Benchmarks and metrics developed for model inference, fine-tuning, and energy consumption of large-scale AI workloads will be contributed to the open-source community.