Run Your Polars Code on Multiple GPUs | Live with cuDF Polars

Polars is one of the fastest-growing DataFrame libraries in the Python ecosystem, and now you can easily run your Polars code on a GPU, as well as seamlessly scale to multiple GPUs. In this live session, Brian Tepera (PM for NVIDIA) will walk through a Polars workflow and then show the audience how to scale up to multiple GPUs. What you'll learn: - How the Polars GPU engine scales a single Polars query across multiple GPUs - How to stand up a multi-GPU run with cudf-polars without rewriting your query - How the multi-GPU engine compares to Polars' CPU streaming engine on real group-by, aggregation, and join workloads Join us as we run the code and answer questions throughout the session. ⬇️ Demo notebook → https://github.com/rapidsai-community/showcase/blob/main/accelerated_data_processing_examples/multi_gpu_polars_demo.ipynb 📚 cuDF Polars docs → https://docs.rapids.ai/api/cudf/stable/cudf_polars/ 📚 Polars GPU Support → https://docs.pola.rs/user-guide/gpu-support/ 💻 cuDF on GitHub → https://github.com/rapidsai/cudf 👥 Share feedback → https://github.com/rapidsai/cudf/issues