llama.cpp
dfceb012
- llama : add "virtual sequences"
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
llama : add "virtual sequences" ggml-ci
References
gg/llama-high-throughput-rebase
Author
ggerganov
Committer
ggerganov
Parents
30b4d4e1
Loading
