Oxidize Lightning Talks – Friedrich Rockenbauer
summary
Company Didalian moves from a massive Python ML stack to Rust for middleware after half the codebase rewritten in two weekends, keeping C++ for a no-stdlib, real-time scheduler. The Rust parts handle millions of images for annotation and inference, improve performance and reliability, and attract hires; ML tooling in Rust remains immature so experiments continue, and first Rust components into the hard real-time path are planned but not yet deployed.
AI-written summary · about
related talks
20mMastering Rust on Edge and Cloud — AI/IoT Case Studies
13mLightning Talk: From ‘We Want Rust’ to ‘We Have a Rust Team’ — The Journey...
12mLightning Talk: Rust Will Solve All Your Problems, Possibly. Arm’s Journey to Using...
39mReal-Time Rust in Robotics
27mHow to switch from cozy NodeJS to scary Rust as a company.
59mRust in Production
19mEnhancing Gen-AI with Rust: Scalable AI Systems
38mPanel: Rust in reality