Misc. bug: UMA detection incorrectly limits available memory on AMD APUs with large TTM allocations

在 AMD APU(如 Strix Halo / gfx1151)上运行 llama.cpp 的 HIP/ROCm 后端时,UMA 检测逻辑会把 GPU 可用显存误判为系统 RAM 的 MemAvailable ,导致 llama_params_fit 错误缩小上下文或把层卸载到 CPU。优先排查该








