Comment on Very large amounts of gaming gpus vs AI gpus
AreaKode@lemmy.world 2 months agoLLMs are experimental, alpha-level technologies. Nvidia showed investors how fast their cards could compute this information. Now investors can just tell the LLM what they want, and it will spit out something that probably looks similar to what they want. But Nvidia is going to sell as many cards as possible before the bubble bursts.
whyNotSquirrel@sh.itjust.works 2 months ago
so… GPU were for crypto before, now it’s for LLM, weird world we live in
AreaKode@lemmy.world 2 months ago
Any time you need a CPU that can do a shit load of basic math, a GPU will win every time.
iopq@lemmy.world 2 months ago
You can design algorithms specifically to mess up parallelism by branching a lot. For example, if you want your password hashes to be GPU-resistant.
KeenFlame@feddit.nu 2 months ago
And all other great reasons to use excessive branching