llama.cpp

480160d4 - ggml-webgpu: Fix GGML_MEM_ALIGN to 8 for emscripten. (#18628)

ggml-webgpu: Fix GGML_MEM_ALIGN to 8 for emscripten. (#18628) * Fix GGML_MEM_ALIGN to 8 for emscripten. * Add a comment explaining the need for GGML_MEM_ALIGN == 8 in 64-bit wasm with emscripten