Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU
(
github.com/xaskasdf
)
381 points
by
xaskasdf
1 day ago
|
past
|
96 comments
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
