The scheduler updates free VRAM based on current loaded models. This was
mutating the persisted list of GPUs, and when coupled with the non-refreshing
logic for Metal that lead to stale low VRAM reporting after unload. The fix is
to make sure the GPU discovery always returns a copy so the schedulers GPU list
is in fact ephemeral and doesn't leak any temporary adjustments back into the
persistent list.
6aa7283076