2219
Save The Planet (lazysoci.al)
submitted 1 year ago by to c/microblogmemes@lemmy.world
288 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 1 year ago (1 child)

My guy, we're not talking about just leaving a model loaded, we're talking about actual usage in a cloud setting with far more GPUs and users involved.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 1 year ago (1 child)

    So you think they're all at full load at all times? Does that seem reasonable to you?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 1 year ago (1 child)

    Given that cloud providers are desperately trying to get more compute resources, but are limited by chip production - yes, of course? Why do you think they're trying to expand their resources while their existing resources aren't already limited?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 1 year ago (1 child)

    Because they want the majority of the new chips for training models, not running the existing ones would be my assertion. Two different use cases

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 1 year ago (1 child)

    Sure, and that's why many cloud providers - even ones that don't train their own models - are only slowly onboarding new customers onto bigger models. Sure. Makes total sense.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •