DeepSpeed
368a7630
- Refine the FP16-to-FP6 cast logic.
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
Refine the FP16-to-FP6 cast logic.
References
#5234 - FP6 quantization end-to-end.
Author
JamesTheZ
Committer
JamesTheZ
Parents
ff6c3c3a
Loading