llama.cpp
5a77ac71
- Relax requirement of checks in async CUDA copies from backend and buffer type to just buffer type, to avoid linking issues
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
45 days ago
Relax requirement of checks in async CUDA copies from backend and buffer type to just buffer type, to avoid linking issues
Author
aendk
Committer
ggerganov
Parents
5fba5961
Loading