Picked up an old Tesla P100 accelerator card off eBay quite cheap, managed to get it working in my home server.

Had to print up some ducts to add active cooling (they're usually cooled by the airflow within the server they're installed in), added a little fan smoother/adjuster and a few brackets to hold the (massive) card in place, then whipped up a little helper utility that reads from nvidia-smi GPU temp data to set the 12v fan speed as I was having issues getting fancontrol to read nvidia's i2c values in a useful way.

It's still a bit too noisy when under load, the fan I've got doesn't rotate until you apply at least 40% of the PWM cycle as it's a big-boi, so might look at getting a couple of smaller fans perhaps, just want to make sure the thing doesn't cook.

#MachineLearning #LocalAI #AI #ML #Nvidia #Linux #Hardware #3dprinting #cooling

Just set up #LocalAI with #stablediffusion on my #homeserver!
Here are a few images i've generated so far:

Loving the new #OpenAI integrations with #nextcloud ... especially that they work with #localai ! My only complaint: now I want AI EVERYWHERE in Nextcloud! Give me AI in Flows, give me AI chat, more more more!

CNCF published an overview and demo of k8sgpt. Run an LLM locally on consumer hardware!

https://community.cncf.io/events/details/cncf-cncf-online-programs-presents-cncf-on-demand-webinar-localai-meets-k8sgpt/

#chatgpt #k8sgpt #localAI

Want to run an AI model on your machine? Check out https://github.com/go-skynet/LocalAI

Want to run it on your Edge Kubernetes device? Then check this out https://kairos.io/docs/examples/localai/

Very excited about the cool features we're working on at the Open-Source department of Spectro Cloud

#opensource #ai #LocalAI #KairosOS #chatgpt