Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
DeathArrow
30 days ago
|
parent
|
context
|
favorite
| on:
Taking on CUDA with ROCm: 'One Step After Another'
Do we get better perf or tokens per second with AMD and its software stack than with Nvidia?
wongarsu
30 days ago
[–]
The metric where AMD usually comes out on top is perf/$. Or with their instinct cards VRAM/$
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: