About FP8 Quantization #312
Unanswered
1145284121
asked this question in
Q&A
Replies: 1 comment
-
|
No, FP4 and INT4 with SVDQUANT is already very close to BF16 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Have your team tried using FP8 quantization? The accuracy will be better compared to NF4/INT4? Also, are there any plans to support it in the future?
Beta Was this translation helpful? Give feedback.
All reactions