Welcoem to posts!!
in the future - u will be able to do some more stuff here,,,!! like pat catgirl- i mean um yeah... for now u can only see others's posts :c
@EttoreDiGiacinto and LocalAI team released version 2.20 (2.20.1) github.com/mudler/LocalAI/releases with the community pools!
What say you after seeing some of our distributed testing on the channel?
Work and home remodels have kept me out of the lab recently - more coming. Should we do Mistral Large? Play with some ORPO models? Instructional?
2 - 0
🦙🔥
10 - 0
Hacking around with LocalAI Distributed Inference (localai.io/features/distribute/) in Kubernetes.
This will be game-changing for the Local LLM running community. Federated servers and llama.cpp worker nodes. Yeah that's right running models across machines on a network or internet - Think community driven hardware pools for the future (github.com/mudler/LocalAI/issues/3113) can't fit more GPUs, just add another machine with more!
Thanks to the open-source community for bringing this live and @EttoreDiGiacinto for bringing it to LocalAI!
11 - 2
Midweek lab update! Said goodbye to some of the 4060's today, as they are leaving to join a lucky viewers lab...Happy trails little fellas!
Special thanks to that viewer for supporting the channel! I won't call you out, but if you want to claim and tell community the amazing work you are going to use them for please do.
Don't worry I still have several 4060's for testing in the lab, these were replaced by the A4500's. Question is - if and what do we add to lab for testing? AMD? Intel? Nothing, so the wife doesn't freak out? More pizza to keep the AI happy?
13 - 4
3090 this, 3090 that - ok, ok one landed in the lab today......
12 - 4
Llama 3.1 models released today... are you already downloading them?
0 - 3
Whoa 100+ subscribers? Originally this was just videos to settle some questions between friends and continue to answer other questions. Can't thank everyone enough - stay tuned for more! Remember to buy your AI a pizza.
3 - 0
Just another engineer fooling around in a GPU powered Kubernetes based AI/LLM Lab. We play around with different GPUs, different Large Language Models, run tests and see what we can learn together.
I am not an expert, and make bad decisions, please do not follow anything I do on this channel.