[HN Gopher] Ask HN: How would one go about building an API for f...
___________________________________________________________________
Ask HN: How would one go about building an API for fine tuning?
Let's say I wanted to build an API to let users upload images and
the api would fine tune stable diffusion for them returning either
a checkpoint or another api that let's them run inference on the
fine-tuned model. Does anyone have any architecture
considerations/issues they'd suggest? Two things I'm considering:
- Would the problem with this approach of ad-hoc GPUs likely be
cold boot? It would take a shit ton of time to load. Though with
data center networks speeds that wouldn't be too much of an issue -
considering the fine-tuning itself would likely dwarf boot times.
- Is it possible to launch remote GPU instances ad-hoc from code?
Is there a service that provides this service? Every time a call is
made we'd spin up a GPU Maybe the best approach for a V1 is to use
the AWS SDK or something similar to just launch instances as calls
come in. Appreciate the help!
Author : samlhuillier
Score : 3 points
Date : 2022-11-12 20:54 UTC (2 hours ago)
___________________________________________________________________
(page generated 2022-11-12 23:02 UTC)