hipDF documentation#
2025-11-06
1 min read
hipDF enables GPU-accelerated DataFrames based on the Apache Arrow columnar memory format. Its API is similar to that of Pandas, letting you accelerate both your existing and new data science workloads on AMD GPUs with high-level functions that eliminate the need to go into low-level HIP programming. This library enables large-scale data processing on AMD Instinct GPUs, enabling data manipulation tasks such as loading, joining, aggregating, and filtering to be performed on data in GPU memory. hipDF offers both a Python and C++ API, supporting a wide range of use cases. For more information and to learn about what’s new in the latest release, see What is hipDF?
The hipDF code is open and hosted at ROCm-DS/hipDF.
The hipDF documentation is structured as follows:
To contribute to the documentation refer to Contributing to ROCm-DS.
You can find licensing information on the Licenses page.