Xiaoyu Xu
Xiaoyu Xu
> Would it not be better to just drop the memory and reload tensors from the model file on disk that you already have? ComfyUI’s unload and load operations work...
> Agree. This is the same behaviour as swap. I actually have some work-in-progress for what @asagi4 describes by just going back to the model file in this scenario. Going...
> How does this interact with pinned memory? My understanding is mmaped memory cannot be inplace pinned using the apporach currently taken in pin_memory (cuda_host_register). Does this just error and...
> This is a disruptive change and the community has actually gone to the effort of explictly offloading mmaps in the past due to poor OS support. > > https://github.com/city96/ComfyUI-GGUF/blob/main/nodes.py#L98...