GLM 4.7-Flash / Vulkan RADV native PP512/TG128

User reports GLM-4.7-Flash at 73 t/s generation and 990 t/s prompt processing on an AMD Strix Halo 128GB system with a single Radeon 8060S iGPU. Setup is llama.cpp with UD-Q4_K_XL, full offload, batch 2048 and flash attention, measured via llama-bench pp512 and tg128. The 990 t/s and 73 t/s are separate 512-token prompt and 128-token generation microbenchmarks, not one end-to-end request; repetition count, context allocation and cache type are not published.