LocalLLaMA
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.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
view the rest of the comments
My problem isn't much GPU dying, or getting not powerful enough, but that as we work in a "certified environment", everyone sourcing can't procure anymore a GPU model, we can't just buy the next generation and assume it works, but have to run an extensive list of test, then update documentations including list of supported GPU per system version(especially for service) .
Basically, it's the kind of stuff where you can loose a lot of time (and which isn't always high on priority list) so feel like as soon as we finally approved the usage of a GPU version, we have our suplier telling us it's not available anymore. I would love to have a GPU manufacturer offering 10-15 years of market availability (Like we get for FPGA) .