llama.cpp

5a23695d - ggml-webgpu: Update register tiling matmul to use f32 accumulation (#21644)

ggml-webgpu: Update register tiling matmul to use f32 accumulation (#21644) * Update register tiling matmul to use f32 accumulation * fix profiling code * Fix register tiling matmul for chrome, i'm blaming dawn * Update batch tuning value for iOS * compile fix * Fix use of new load function