Andray

``` GPU MX150 2GB ARGS: export PYTORCH_CUDA_ALLOC_CONF=backend:cudaMallocAsync ./webui.sh --xformers "$@" + fp8 4 steps 512x512 --lowvram Time taken: 22.1 sec. A: 0.96 GB, R: 1.19 GB, Sys: 1.3/1.95508 GB (66.0%)...

The same vram usage, but slower... ``` This patch, no xformers and no PYTORCH_CUDA_ALLOC_CONF Time taken: 23.2 sec. A: 1.25 GB, R: 1.85 GB, Sys: 1.9/1.95508 GB (99.2%) ```

> One thing interesting is that the lowvram goes faster than medvram. Can you upload a nsys profile? Yes, but hires vram usage. 93% vs 99% XD

> May be your actual compute work is lagging behind. Use `nsys` to figure out. Can't install... Installed `sudo apt install nsight-systems`, but there are only nsys-ui, which doesn't work...

I have only `nsys-ui` after installation. Maybe I need to reboot pc, but I'm afraid because Qt incompatible error. It's a bad signal, maybe I wont be able to boot...

@wfjsw check discord PM

It still uses more vram then medvram ``` Time taken: 17.2 sec. A: 1.27 GB, R: 1.85 GB, Sys: 2.0/1.95508 GB (99.9%) ```

Do you mean save the image only inside the grid directory?

For me it can happens ramdomly. I think it's restriction of gradio, is wasn't designed for very big applications. I use "refresh" button to see loras

For problems like in your screenshot - I've made the same refresh button in PR: - https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14857 Hope it will be merged