DeepSpeed
d2997bf4
- add q-int4 on top of q-int8
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
add q-int4 on top of q-int8
Author
Reza Yazdani Aminabadi
Parents
2ce22d7d
Loading