ROCm-DS is an open-source software toolkit built on the ROCm™ platform, enabling high-performance data science and data processing workloads. The acceleration offered through ROCm-DS allows you to process larger datasets and execute more complex workloads in a timely manner. With ROCm-DS, you can access the full power of AMD GPUs, which can significantly improve the performance, productivity, and computational capabilities of data science workloads.
ROCm-DS 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. With ROCm-DS, 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.
ROCm-DS 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 ROCm-DS documentation.