Ask HN: How to build GPU compute marketplace?

Posted by michaeloblak on Wednesday April 12, 2023 @07:28PM
from the ask-hn dept.

Is it possible? Let's say Alice has 2 GPUs idle at the moment, Ben has 1 GPU, and Chris needs 3 GPUs for the next 12 hours. How to build such a system, and what problems there might occur? How to handle turning off one's machine? Does it even make sense to run training or inference on such (latency)?

( 4 comments | on HN )

Re:Ask HN: How to build GPU compute marketplace? by ftxbro on Wednesday April 12, 2023 @07:29PM (#35548545)

There is already some like this including vast dot ai.

[ Parent | on HN ]

Re:Ask HN: How to build GPU compute marketplace? by michaeloblak on Wednesday April 12, 2023 @07:39PM (#35548667)

Yeah, but how does it work exactly? Dropbox is rsync with UI, Instagram is a blog with pictures, but this?

How to access one’s compute? Overriding GPU drivers?

[ Parent | on HN ]

Re:Ask HN: How to build GPU compute marketplace? by deserialized on Wednesday April 12, 2023 @09:05PM (#35549474)

It's just a remote docker context on a machine with the nvidia driver and container runtime already installed that you rent by the hour.

[ Parent | on HN ]

Re:Ask HN: How to build GPU compute marketplace? by brucethemoose2 on Wednesday April 12, 2023 @07:57PM (#35548855)

More task specific compute pools (like Stable Horde) make lots of sense where applicable.

[ Parent | on HN ]