text-generation-inference
4844ff79
- fix(server): fix fp8 weight loading (#2268)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
fix(server): fix fp8 weight loading (#2268) * fix(server): fix fp8 weight loading * fixed scales loading * update snap * revert default dtype
References
#2268 - fix(server): fix fp8 weight loading
Author
OlivierDehaene
Parents
6aebf44f
Loading