model: meta-llama/Llama-3.1-8B-Instruct
host: "0.0.0.0"
port: 8001
uvicorn-log-level: "info"
gpu-memory-utilization: 0.70
max-model-len: 16384
dtype: auto
enforce-eager: false
enable-auto-tool-choice: true
tool-call-parser: "llama3_json"