auto-round
b3ef561d
- skip quantizing mtp.fc since vLLM doesn't support (#1731)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
29 days ago
skip quantizing mtp.fc since vLLM doesn't support (#1731) Signed-off-by: Xin He <xin3.he@intel.com>
References
#1731 - skip quantizing mtp.fc since vLLM doesn't support
Author
xin3he
Parents
c2344554
Loading