Activate model on GPU (WARM → ACTIVE).
uint64_t host_memlock_limit_bytes()
This process's RLIMIT_MEMLOCK soft limit (gh#148).
@ optional
optional: every escape asks the host's path approver
uint64_t query_device_free_vram_bytes()
Free VRAM on the first GPU device ggml reports, in bytes.
uint64_t device_memory_query_count()
How many device free-VRAM queries this process has made (gh#198).