Function default_device 

pub fn default_device() -> usize

Which GPU this thread’s engine calls address. Multi-card hosts hold one wgpu context PER card (weights, KV mirrors and scratch live inside a context, so per-device contexts give per-device caches for free); this thread-local says which one is current. Default: the process pin (CMF_GPU_ADAPTER) or 0 — so single-card runs behave exactly as they always have.