fprintf(stderr,"%s: [cublas] total VRAM used: %zu MB\n",__func__,vram_total/1024/1024);
}
#else
(void)n_gpu_layers;
#endif
// loading time will be recalculate after the first eval, so
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.