llama.cpp
cac8d7b2
- fix small draft case
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
83 days ago
fix small draft case
References
#17808 - server: improve speed of speculative decoding
#51 - (FOR CI) Xsn/server improve spec
Author
ngxson
Parents
f2f08f84
Loading