llama.cpp
b436edaa
- server : take into account speculative limits
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
server : take into account speculative limits ggml-ci
References
#10641 - server : fix speculative decoding with context shift
Author
ggerganov
Committer
ggerganov
Parents
a5a915b5
Loading