LocalLLaMA

2884 readers

6 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

founded 2 years ago

MODERATORS

pax@sh.itjust.works

SkySyrup@sh.itjust.works

noneabove1182@sh.itjust.works

Smokeydope@lemmy.world

MonsterBug@sh.itjust.works

A question about running LLMs with an AMD card (self.localllama)

submitted 1 year ago by gunpachi to c/localllama@sh.itjust.works

16 comments fedilink hide all child comments

On my machine I'm running opensuse tumbleweed and has the amdgpu driver installed. I use it for gaming and recently I've become interested in running LLMs. So I would like to keep a balance of both without compromising too much on performance.

I know that there are proprietary drivers for AMD cards but I'm hesitant to install it as I've heard that it performs less efficiently in games when compared to the open source driver.

I'm mainly confused about this ROCM thing. Is it not included with the opensource amdgpu drivers ? Or is it available as a separate package?

So what driver to use ?

Or perhaps, is it possible to run oogabooga or stable diffusion within a distrobox container (with the proprietary drivers) and still keep using the open source gpu drivers for the Host operating system.

you are viewing a single comment's thread
view the rest of the comments

[–] taladar@sh.itjust.works 9 points 1 year ago (3 children)

To do general purpose GPU calculations on AMD hardware you need a GPU that is supported by ROCm (AMD's equivalent to CUDA). Most of the gaming GPUs are not.

There is a list here but be aware that that is for the latest rocm version, some tools might still use older versions with different supported devices.

https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html#supported-gpus

[–] madnificent@lemmy.world 5 points 1 year ago (2 children)

Has that changed recently? I've ran ROCm successfully on an RX6800. I seem to recall that was supported, the host OS (Arch) was not.

[–] taladar@sh.itjust.works 1 points 1 year ago

When I tried it maybe a year or so ago there were four supported chipset in that version (5.4.2 I think) of rocm but I don't remember which card models those were since they were only specified in that internal chip name. Mine wasn't supported at the time (5700XT)

[–] turbodrooler@lemmy.world 1 points 1 year ago

No, GFX1030 is still supported.

[–] turbodrooler@lemmy.world 3 points 1 year ago

This link is misleading. For example, the Radeon RX6800 IS supported because it is the same chip as one of the Radeon Pros. GFX1030. Many others are too…though support does not go very far back.

[–] exu@feditown.com 1 points 1 year ago

Llama.cpp supports OpenCL as well and performs better than rocm in my limited experience. That should work on basically any GPU.