Nvidia announces native GPU programming in Rust
- ID
- 25401
- Status
- summarized
- Published
- 16 Sep 2026, 7:15 PM
- Fetched
- 18 Sep 2026, 4:53 PM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://developer.nvidia.com/blog/introducing-cuda-rust-two-tracks-for-writing-gpu-kernels/
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.0
- Created
- 18 Sep 2026, 4:54 PM
- Tags
- Audience
- developersai_ml_learners
What happened
NVIDIA announced two tracks for writing GPU kernels natively in Rust: cuda-oxide (SIMT-style, compiles to PTX via custom rustc backend, requires nightly Rust, early alpha) and cutile-rs (Tile-based, runs on stable Rust 1.89+ with CUDA 13.3, already published on crates.io and used in HuggingFace's Grout inference engine and mistral.rs). Both enforce compile-time memory safety—cuda-oxide via DisjointSlice and launch contracts, cutile-rs via tensor partitioning and ownership.
Why it matters
If you write or maintain GPU kernels, cutile-rs is usable today on stable Rust and already runs in real inference engines, so you can evaluate it as a safer alternative to CUDA C++ for kernel work without switching toolchains. cuda-oxide is too early for production but worth tracking if you need SIMT-level control. NVIDIA also plans interop between CUDA Rust, C++, and Python, so choosing a Rust frontend won't lock you out of existing CUDA ecosystems.
Discussion angle
Compare the two tracks practically: cutile-rs is stable and production-tested (Grout, mistral.rs) while cuda-oxide needs nightly Rust and custom LLVM—is the Tile abstraction enough for most kernel work, or do you still need SIMT control?