llama.cpp
c7facb0f
- cont : async drft eval when possible
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
10 days ago
cont : async drft eval when possible
References
#22838 - spec : parallel drafting support
Author
ggerganov
Committer
ggerganov
Parents
08c8012b
Loading