Hi, this is actually pretty important for my business. I've been waiting for the driver to be released for a year now. We got the binary a few months ago under NDA, but open sourcing it, is next level for us.<p>What I wrote about this on twitter: <a href="https://x.com/HotAisle/status/1914549886185611627" rel="nofollow">https://x.com/HotAisle/status/1914549886185611627</a>
related:
(AMD 2.0 – New Sense of Urgency)<p><a href="https://news.ycombinator.com/item?id=43780972">https://news.ycombinator.com/item?id=43780972</a>
It blows my mind how reliably AMD shoots itself in the foot. What we want isn’t that hard:<p>1) Support your graphics cards on linux using kernel drivers that you upstream. All of them. Not just a handful - all the ones you sell from say 18 months ago till today.<p>2) Make GPU acceleration actually work out of the box for pytorch and tensorflow. Not some special fork, patched version that you “maintain” on your website, the tip of the main branch for both of those libraries should just compile out of the box and give people gpu-accelerated ML.<p>This is table stakes but it blows my mind that they keep making press releases and promises like this that things are on the roadmap without doing thing one and unfucking the basic dev experience so people can actually use their GPUs for real work.<p>How it actually is:
1) Some cards work with rocm, some cards work with one of the other variations of BS libraries they have come up with over the years. Some cards work with amdgpu but many only work with proprietary kernel drivers which means if you don’t use precisely one of the distributions and kernel versions that they maintain you are sool.<p>2) Nothing whatsoever builds out of the box and when you get it to build almost nothing runs gpu accelerated. For me, pytorch requires a special downgrade, a python downgrade and a switch to a fork that AMD supposedly maintain although it doesn’t compile for me and when I managed to beat it into a shape where it compiled it wouldn’t run GPU accelerated even though games use the GPU just fine. I have a GPU that is supposedly current, so they are actively selling it, but can I use it? Can I bollocks. Ollama won’t talk to my GPU even though it supposedly works with ROCm. It only works with ROCm with some graphics cards. Tensorflow similar story when I last tried it although admittedly I didn’t try as hard as pytorch.<p>Just make your shit work so that people can use it. It really shouldn’t be that hard. The dev experience with NVidia is a million times better.
Anyone else find it funny that AMD releases new GPU features while people still can't get basic ML stuff working? It's like building a fancy garage before fixing the broken car.