AMD Data Science is an open-source software toolkit built on the ROCm™ platform, enabling high-performance data science and data processing workloads. The acceleration offered through AMD Data Science allows you to process larger datasets and execute more complex workloads in a timely manner. With the AMD Data Science library, you can access the full power of AMD GPUs, which can significantly improve the performance, productivity, and computational capabilities of data science workloads.
AMD Data Science is a fork of the RAPIDS® open-source project from NVIDIA, extended and optimized for AMD GPUs. It enables users to accelerate both new and existing data science workloads, executing intensive applications with larger datasets at exceptional speed. Using AMD Data Science you can build pre- and post-processing applications for AI models, create big data processing workloads, or accelerate existing data science pipelines with minimal effort.
AMD Data Science delivers a cohesive set of libraries that target every stage of the data science lifecycle, from data ingestion and transformation to graph analytics, mathematical computation, and vector search. Each component is optimized for GPU performance while maintaining user-friendly interfaces compatible with existing data science frameworks and APIs. For more information, see the AMD Data Science documentation.