Running this code with cargo run
and let it scan ports from localhost where llm server is hosted, if it found a port to use, it will write down the ip address, port and response time to an output folder.
Pull with git:
git pull git@github.com:nhatnm0612/lm-server-rust.git
Cd into new directory:
cd lm-server-rust
Run with cargo:
cargo build -vv
cargo run
Run test with cargo:
cargo test -vv
Run with cargo in dev environment:
ENVIRON=dev cargo run
Fake server in ./dev/main.py
is a Python FastAPI Server mimicking OpenAI completions route. Used for development only.