Hacker Times
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
unrvl22
43 days ago
|
parent
|
context
|
favorite
| on:
Performance per dollar is getting faster and cheap...
MI355X can perform FP6 operations with the same speed as their FP4 (unique to AMD) - people should be making MXFP6 quants which would be pretty much lossless, and much closer to FP4 performance than FP8
Hugsun
43 days ago
[–]
That can only be true if the workload is compute bound, not memory bandwidth bound.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
