compute-runtime VS automatic

Well... Fuck! https://github.com/intel/compute-runtime/issues/643

For what it's worth, I was able to get IOMMU enabled and iGPU passthrough working for Plex on an Ubuntu 22.04 LXC container with a fresh install of Proxmox 8.0.3 (kenrel 6.2.16-3-pve) on an Intel i5-13400, ASRock B760M Pro RS/D4, also using Intel drivers released early today. I largely followed this guide.

For this little project unless someone chimes in with experience or can point to regarding the RX 6600 XT / 6650 XT / perhaps 7600 I might go with https://github.com/intel/compute-runtime . (They don't have perfect documentation re supported gpus either, the readme table doesn't list DG2, you need to go to releases to see that) . Phoronix reported it as pretty stable when they tested it with kernel 6.2 in March.

Update: I was able to fix my issue. I'm using Ubuntu 22.04.2 LTS and have the newest available kernel, 6.3.1. Installing the drivers via apt does not work, instead I needed to use https://github.com/intel/compute-runtime/releases/

Drivers: https://github.com/intel/compute-runtime/releases

wget https://github.com/intel/compute-runtime/releases/download/22.43.24595.30/intel-level-zero-gpu-dbgsym_1.3.24595.30_amd64.ddeb

For OpenCL HDR/DV tone-mapping, install the extra compute-runtime if running on host.

> it won't ever be a viable option

For production workloads, I generally agree. It's an unsupported hack with a questionable future, I wouldn't do anything money-making with it.

However, for tinkering and consumer workloads, it already works pretty well. Enough of cuDNN and cuBLAS work to run PyTorch and in turn, Stable Diffusion with https://github.com/lshqqytiger/ZLUDA - there's even a fairly user-friendly setup process already in https://github.com/vladmandic/automatic .

I was able to get a personal non-ML related project working on my AMD card in just a few minutes, which saved me a lot of development time before I then deployed the production workload on NV hardware (this is probably why AMD pulled the plug on the project - it's almost more of a boost to NV than anything else, AMD really need people to be writing code on ROCm to deploy on AMD datacenter hardware).

While I currently use SD.Next[1], I have tested ComfyUI locally with my AMD card. The UI can be daunting, but you learn quite a great deal about how a Stable Diffusion pipeline works. In addition some innovations and advances find their way into ComfyUI first.

[1] https://github.com/vladmandic/automatic

I used SD.NEXT ( https://github.com/vladmandic/automatic ) and https://civitai.com/models/82098/add-more-details-detail-enhancer-tweaker-lora and epicphotogasm_lastUnicorn

I found this thread on GitHub talking about how this was fixed in the latest version with an optional setting. I tried enabling it, as they mentioned, but it just resulted in an immediate CUDA out of memory error when starting generation. So it seems I'm actually needing the shared memory, which I assume is my issue.

As always, do check out our more detailed changelog, give us a quick install from our Repo, and stop by our Discord Server for any questions or help you may need.

SD.Next

Today I finally wanted to give SDXL a chance, so I set everythin up according to Vladmandic's Wiki https://github.com/vladmandic/automatic/wiki/SD-XL

I'm trying to get SDXL working on Vlad's SDNext, but I keep getting the error in the title when trying to run basic operations. I'm not sure what's going on, I followed his guide for it to a T.

We used an inference container based on SDNext, along with a custom worker written in Typescript that implemented the job processing pipeline. The worker used HTTP to communicate with both the SDNext container and with our batch framework.