llama.cpp

a95a11e5 - ggml-webgpu: Improve performance of mat-vec and mat-mat for MUL_MAT_ID (#22464)

ggml-webgpu: Improve performance of mat-vec and mat-mat for MUL_MAT_ID (#22464) * Add mat-vec fast path of MUL_MAT_ID. * Add shared accumulation vec logic and the other types supports. * Add i-quant mat-mat for MUL_MAT_ID and fix some parts * Remove n_experts from shader_lib_context.