cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
In September 2026, NVIDIA announced it is leaning into native GPU programming in Rust. CUDA C++ and CUDA Python are mature, enterprise-grade toolchains, and NVIDIA will be growing and maturing CUDA…
Serve and scale open-source and custom AI models on the fastest, most reliable inference platform.
CoreWeave is the force multiplier that empowers pioneers with momentum, magnitude, and mastery—enabling them to innovate with confidence. Explore the #1 AI Cloud.
Train and scale AI on NVIDIA VR200 NVL 72, GB300 NVL 72, B300, B200, H200, H100, and and more GPUs. Launch on-demand instances or reserve a cluster. Get started.
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.