Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
fzzzy
on Dec 28, 2024
|
parent
|
context
|
favorite
| on:
All You Need Is 4x 4090 GPUs to Train Your Own Mod...
Thanks, good to know. Perhaps it is different for diffusion; with llms, layers are generally split across gpus, meaning inference has to happen on one gpu before the values can be passed between the layer split.
Y_Y
on Dec 28, 2024
[–]
That's only if your model is too big for a single GPU and you're not batching.
fzzzy
on Dec 29, 2024
|
parent
[–]
Yes, that's what I was doing. Thanks for the info.
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: