Did you consider other use cases in which people need custom models and inferenc... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		akoculu 6 months ago \| parent \| context \| favorite \| on: We were wrong about GPUs Did you consider other use cases in which people need custom models and inference other than just open source LLMs ?

tptacek 6 months ago [–]

Yes. Click through to the L40S post the article links to (the L40S's aren't going anywhere).

There are people doing GPU-enabled inference stuff on Fly.io. That particular slice of the market seems fine?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact