rakataprime

did u set performance to manual with feature mask set like `rocm-smi --setperflevel manual ` ` rocm-smi --setvc 2 1701 915 --autorespond y` ` rocm-smi --setsrange 808 1740 --autorespond y`

@hinthornw I would gladly take a shot at trying to complete this. Is there an recommended starting place for what OSS models / API are easiest to add support for...

I have a dev server with 2 4090s (24gb VRAM) but also can use a100 / a6000 cards if the larger models would improve the performance. I have been interested...

this is a bug likely with input resolution of the mask being off or drawing a mask in a weird way. there aren't any checks for checking x1 < x2...

@grummelgrisgram , in your first screen shot you have inpaint area set to full picture. Wouldn't that not have a sharp inpainting boundary? What happens with inpaint area set to...

So if we look at the two tiers of gpus we still have a lot of variation within those tiers. Tier 1 H100, A100, V100, P100, A40, A10, P4, K80,...

@anilmurty, if you don't actively try to coral the providers into standardized cuda versions it would prevent people from running training jobs like foundation models across multiple providers because the...

@anilmurty , I think someone should test the torchbench sdl on the gpu testnet before we say its usable. I believe it is currently usable, but should test that assumption...

@anilmurty the latest commit adds jupyter and an example notebook. It still needs to be tested on testnet. Also the juypter notebook implementation requires users to paste in the auth...

I have similar issues with rocm-smi settings changes on Radeon VII with rocm version 5.4.1 with kernel 5.15.0-58-generic on Ubuntu 20.04.1. settings i have tried include powercap, clock speeds, and...