Previous discussion in September when they didn't have distributed processing: <a href="https://news.ycombinator.com/item?id=41496033">https://news.ycombinator.com/item?id=41496033</a><p>Github Repo: <a href="https://github.com/lakehq/sail">https://github.com/lakehq/sail</a><p>Few interesting notes:<p>- Benchmarks show 4x faster than Spark on TPC-H with 94% cost reduction.<p>- Currently at 65.7% PySpark test compatibility(they talk about this in more detail in the post)<p>- Built in Rust using Tokio runtime and Arrow IPC for high performance<p>- Already supports 79/99 TPC-DS queries