llama.cpp
BetaFerentin's endpoint agent finds llama.cpp on managed Macs from its running process, and every device it is on appears in your shadow AI inventory.
- Local Runtime
- Local Inference
- Found by
- Process
- AI runs
- On the device
- Platform
- macOS
- Vendor
- ggml
How Ferentin governs llama.cpp
Endpoint rules can allow or block the network destinations llama.cpp reaches from managed Macs.
About llama.cpp
llama.cpp local inference runtime
Frequently asked about llama.cpp
- How does Ferentin find llama.cpp?
- Ferentin's endpoint agent for macOS recognizes llama.cpp from its running process. Every managed Mac it is on appears in your shadow AI inventory.
- How do I govern llama.cpp with Ferentin?
- Enroll your Macs with the Ferentin endpoint agent and llama.cpp appears in your shadow AI inventory wherever it is found. You can then write endpoint rules for the network destinations it reaches.
- Is the llama.cpp integration generally available?
- The llama.cpp integration is currently beta on Ferentin.
