Russ

All I wanted them to change was the fact that the installer for the game in 2020 would download then decompress one file at a time, so it took forever for the game to install (on top of the fact that it uses an in-game installer in the first place).

I don’t have the new version, but based on what I’ve been reading they sure curled the monkey paw this time.

Primarily I use Arch on my desktop (and by proxy, my Steam Deck which runs SteamOS), which is what I’ve landed on after a ton of distro hopping. The idea of Atomic distros catches my eyes, but for me in its present state there are too many steps needed in order to make deeper changes (for example, installing a kernel module) - but I quite like SteamOS on my Deck since I know it will always be in a “consistent” state, for example.

On servers I run a mix of Rocky Linux and Debian.

(inb4 ethernet over HDMI: There is no implementation of the spec in the wild).

How about Thunderbolt? This looks like macOS, and while I’m not 100% sure if they utilize HDMI ports anymore, they certainly use Thunderbolt.

I know the feeling, I just had a week off and returned to work on Friday a couple of days ago.

Hmm, gotcha. I just tried out a fresh copy of text-gen-webui and it seems like the latest version is borked with ROCM (I get the CUDA error: invalid device function error).

My next recommendation then would be LM Studio which to my knowledge can still output an OpenAI compatible API endpoint to be used in SillyTavern - I’ve used it in the past before and I didn’t even need to run it within Distrobox (I have all of the ROCM stuff installed locally, but I generally run most of the AI stuff in distrobox since it tends to require an older version of Python than Arch is currently using) - it seems they’ve recently started supporting running GGUF models via Vulkan, which I assume probably doesn’t require the ROCM stuff to be installed perhaps?

Might be worth a shot, I just downloaded the latest version (the UI has definitely changed a bit since I last used it) and just grabbed a copy of the Gemma model and ran it, and it seemed to work without an issue for me directly on the host.

The advanced configuration settings no longer seem to directly mention GPU acceleration like it used to, however I can see it utilizing GPU resources in nvtop currently, and the speed it was generating at (the one in my screenshot was 83 tokens a second) couldn’t have possibly been done on the CPU so it seems to be fine on my side.

Ah, strange. I don’t suppose you specifically need a Fedora container? If not, I’ve been using this Ubuntu based distrobox container recipe for anything that requires ROCM and it has worked flawless for me.

If that still doesn’t work (I haven’t actually tried out kobolcpp yet), and you’re willing to try something other than kobolcpp, then I’d recommend the text-generation-webui project which supports a wide array of model types, including the GGUF types that Kobolcpp utilizes. Then if you really want to get deep into it, you can even pair it with SillyTavern (it is purely a frontend for a bunch of different LLM backends, text-generation-webui is one of the supported ones)!

What card do you use? I have a 6700XT and getting anything with ROCM running for me requires that I pass the HSA_OVERRIDE_GFX_VERSION=10.3.0 environmental variable to the related process, otherwise it just refuses to run properly. I wonder if it might be something similar for you too?

It’s like my science used to say in grade school, “100% of people who consume dihydrogen monoxide end up dead”.

Water has quite a few side effects, the evidence is clear!