Zero-Copy GPU Inference from WebAssembly on Apple Silicon
Agam Brahma
tl;dr: on Apple Silicon, a WebAssembly module's linear memory can be shared directly with the GPU: no copies, no serialization, no intermediate buffers. The CPU and GPU read and write the same physical bytes. End-to-end, it works: a Wasm guest fills a matrix in its linear memory, the GPU reads it,...