undefined | Better HN

0 pointsechelon2y ago0 comments

Next to nothing is written that targets this. Not Stable Diffusion, not RVC, not Vall-E, not Tacotron, not Tortoise, ...

Maybe the LLM space is better about this, but the generative media side definitely isn't.

AMD has a market share of 0% here, and nobody publishes models with AMD support.

0 comments

Symmetry2y ago

The things is you can actually run Stable Diffusion.

And I got PyTorch working on my AMD 7900 XT graphics card recently, though it was a bit of a hassle to do so.

godshatter2y ago

You can also run Stable Diffusion in cpu mode, if you don't mind it being slower. I have an NVIDIA card but it's not powerful enough to run it. I'm on Ubuntu.

echelonOP2y ago

> though it was a bit of a hassle to do so.

Incredible understatement. And the diverse set of community tools also breaks down.

We're still a year or more out from proper AMD support in the ecosystem.

coffeebeqn2y ago

Could there be a compiler/transpiler from CUSA to whatever AMD is pushing ?

puzzlingcaptcha2y ago

That's what https://github.com/ROCm/HIPIFY is (as a part of ROCm)

zamalek2y ago

I think it's llama.cpp that simply #defines all cuda_ functions to rocm_ (99% name-name). Porting seems to be that trivial.

j / k navigate · click thread line to collapse