On machine with llama.cpp
.\llama-server -ngl 100 --port 9090 -m <some.gguf> --host 0.0.0.0
When running
cargo run -- --llama http://<llama.cpp_server_IP>:9090
Fun little project that makes a llama.cpp server LLM chat interface using HTMX and Rust
CSSMIT
On machine with llama.cpp
.\llama-server -ngl 100 --port 9090 -m <some.gguf> --host 0.0.0.0
When running
cargo run -- --llama http://<llama.cpp_server_IP>:9090