rullama 0.2.0

Browser-resident Gemma 4 inference: pure Rust → WebAssembly + WebGPU. Loads Ollama's on-disk GGUF blobs and runs the forward pass on the local GPU via hand-written WGSL.

Documentation

1
2

//! Named per-layer weight handles (SWA vs global), backed by tiled wgpu storage buffers.
//! Filled in during M2.