Qwen3.6 35B-A3B-MTP / Vulkan native PP2048 TG128, MTP off

User reports Qwen3.6 at 71.1 t/s generation and 1195 t/s prompt processing on an AMD Strix Halo 128GB machine. Setup is the charlie12345/rocmfp4-llama fork with the ROCmFP4 STRIX hybrid embF16/headQ6 quant, run through Vulkan0 with -ngl 999 -fa 1 -ub 1024 -r 3 and no MTP. The 71.1 t/s is TG128 and the 1195 t/s is PP2048, separate synthetic tests rather than one request; the same campaign's ROCm0 arm reached 63.4 t/s TG128 and 1271 t/s PP2048.