cuda
Everything on Ground Truth tagged “cuda” — 4 items.
A llama.cpp Patch Learns Which Experts to Keep in VRAM While You Type News
An open pull request to llama.cpp tracks which mixture-of-experts submodels get used most during inference and promotes them to GPU memory on the fly, roughly doubling decode speed on an 8GB card in the author's own tests - while slowing other models down.
cuda-oxide Tool
Early-alpha Rust frontend for explicit CUDA SIMT kernel authoring.
cuTile Rust Tool
Experimental Rust tile-kernel toolkit that JIT-compiles through CUDA Tile IR.
NVIDIA Nsight AI (CUDA MCP server) Tool
A vendor-hosted Model Context Protocol server that gives coding agents current CUDA documentation and code examples, plus a self-hosted blueprint for teams that cannot call out. First connection authenticates with an NVIDIA Developer account, and the docs include a one-line command to register it with common agent CLIs.