llama.cpp
13b339bc
- server : do not default to multiple slots with speculative decoding (#17017)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
134 days ago
server : do not default to multiple slots with speculative decoding (#17017) * server : do not default to multiple slots with speculative decoding * cont : fix
References
#17017 - server : do not default to multiple slots with speculative decoding
Author
ggerganov
Parents
2f0c2db4
Loading