llama.cpp
3c4d2b75
- cuda: read memory through NVML if available to avoid initializing a context
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
86 days ago
cuda: read memory through NVML if available to avoid initializing a context Co-authored-by: Pascal <admin@serveurperso.com>
Author
0cc4m
Committer
0cc4m
Parents
5d246a79
Loading
llama.cpp
3c4d2b75 - cuda: read memory through NVML if available to avoid initializing a context
