CUDA Rust on ThoxOS: An Integration Review of NVIDIA's Two Rust GPU Kernel Tracks, with the First THOX Device Qualification on an RTX 4060 Ti, a Same-Day Comparison Against the Production CUDA C++ Kernel, and the ThoxOS GPU Layer

Technical report THOX-TR-2026-11-03, THOX.ai Research. NVIDIA's CUDA Rust offers two ways to write GPU kernels in Rust: cuda-oxide for SIMT and cutile-rs for Tile. We review both, map them onto ThoxOS hosts, and test the Tile track twice: on a host with no GPU, and on a THOX RTX 4060 Ti workstation (sm_89). On the workstation, our FP32 Tile RMSNorm kernel matches the CPU reference on all 6 model shapes tested. Against the production CUDA C++ kernel on the same host and day, the result splits by shape; both figures are dominated by allocation, launch and copy-back, so we make no kernel-versus-kernel speed claim. A CUDA 13.0 toolkit builds the crate but cannot launch a Tile kernel, because the Tile IR assembler ships only with CUDA 13.2 and later. The Tile track is adopted for new NVIDIA kernel authoring behind the ThoxOS GPU layer fallback; the production default stays on CUDA C++.