TechApr 19, 202613 minZero-copy GPU inference on Apple Silicon with WebAssembly and MetalA three-link chain of mmap → MTLBuffer(bytesNoCopy) → Wasmtime MemoryCreator that makes a Wasm linear memory share the same physical bytes as a Metal GPU buffer. Llama 3.2 1B runs at 9ms/token on M1.WebAssemblyMetalAppleSiliconMLXWasmtimeLLM
