News for hackers. Stuff that matters.
Re:Serving 70B-Scale LLMs Efficiently on Low-Resource Edge D... by lxgr on Thursday October 03, 2024 @01:56PM (#41733082)
Oh yes, I could definitely see the privacy-preserving consumer use case creating sufficient demand for efficiency that also bleeds over into the enterprise market.

That's what's happened with power efficiency and ARM CPUs, after all!

Re:Serving 70B-Scale LLMs Efficiently on Low-Resource Edge D... by adam_arthur on Thursday October 03, 2024 @03:21PM (#41733997)
Not sure what you mean: https://aws.amazon.com/ec2/graviton/

Not to speak of managed cloud services that run on ARM under-the-hood/behind the scenes.

Of course ARM isn't inherently cheaper, AMD+Intel could cut prices/margins big and probably be competitive on $/perf

Re:Serving 70B-Scale LLMs Efficiently on Low-Resource Edge D... by lxgr on Friday October 04, 2024 @09:51AM (#41741403)
That's what I mean: ARM was initially attractive in the low-power/low-performance market, then it scaled up to higher and higher power cores (while still staying power efficient), which in turn attracted datacenter customers.
Re:Serving 70B-Scale LLMs Efficiently on Low-Resource Edge D... by adunsulag on Thursday October 03, 2024 @02:52PM (#41733704)
This is where I want highly sensitive healthcare consumers of LLMs to be at. Note summation, suggested diagnosis (provider always in control), and other augmented abilities for the clinical staff without the risk of health care data sent outside the device, or the very local network.