llama.cpp
2b8830af
- examples : do not eval prompt 2 times (close #3348)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
examples : do not eval prompt 2 times (close #3348)
References
#3228 - llama : custom attention mask + parallel decoding + no context swaps
Author
ggerganov
Committer
ggerganov
Parents
a2075615
Loading