From 480edbc06013526e44569c6920f8697d28faecc4 Mon Sep 17 00:00:00 2001 From: Ritchie Vink Date: Mon, 3 Feb 2025 13:34:54 +0100 Subject: [PATCH] docs: Correct Arrow misconception (#21053) --- docs/source/index.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/docs/source/index.md b/docs/source/index.md index 7e1a102833b3..ca33332aca31 100644 --- a/docs/source/index.md +++ b/docs/source/index.md @@ -30,10 +30,12 @@ in Rust, and available for Python, R and NodeJS. data to be in memory at the same time. - **Parallel**: Utilises the power of your machine by dividing the workload among the available CPU cores without any additional configuration. -- **Vectorized Query Engine**: Using [Apache Arrow](https://arrow.apache.org/), a columnar data - format, to process your queries in a vectorized manner and SIMD to optimize CPU usage. +- **Vectorized Query Engine** - **GPU Support**: Optionally run queries on NVIDIA GPUs for maximum performance for in-memory workloads. +- **[Apache Arrow support](https://arrow.apache.org/)**: Polars consume and produce Arrow data often + zero-copy. Note that Polars is not build on a Pyarrow/Arrow implementation. Polars has written all + compute and buffer implementations.