Gemma 4-12B / Vulkan RADV native PP512/TG128

User reports Gemma-4-12B at 14 t/s generation and 716 t/s prompt processing on an AMD Strix Halo 128GB machine with a single Radeon 8060S iGPU. Setup is llama.cpp with the Unsloth UD-Q8_K_XL quant, full offload, batch 2048 and flash attention, using the RADV Vulkan backend. The 716 t/s is native PP512 prompt processing and the 14 t/s is native TG128 generation, run as separate microbenchmarks rather than one end-to-end request; the ROCm arm reports prompt processing only.