llama.cpp
847896ab
- speculative : add --draft CLI arg
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
speculative : add --draft CLI arg
References
speculative
#2926 - speculative : PoC for speeding-up inference via speculative sampling
Author
ggerganov
Parents
a15ca746
Loading