Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
xaskasdf
2 days ago
|
parent
|
context
|
favorite
| on:
Show HN: Llama 3.1 70B on a single RTX 3090 via NV...
I thought about that, but idk if they allow me to modify the linux kernel and nvidia cuda kernel at all
help
jonassm
2 days ago
|
next
[–]
In those systems you could probably leverage something like Nvidia SCADA or GDS directly.
reply
xaskasdf
2 days ago
|
parent
|
next
[–]
Actually since they have direct GDS it should perform really well on professional gpus
reply
green-salt
2 days ago
|
prev
[–]
I think you can do a bunch of that on Digitalocean's GPU droplets.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: