`gl.nvidia.blackwell.tma.async_scatter` functions respectively. TMA gather and scatter operations only support 2D tensor descriptors, where the first dimension of the block shape must be 1. Gather ...
uv init [-p 3.9] uv add shiny source.venv/bin/activate shiny --version shiny --help shiny create --help Create a new Shiny Express app from template: shiny create -g ...