You can deploy it using vllm. And this is the script for deploying.
``` bash
python -O -u -m vllm.entrypoints.openai.api_server \
        --host=127.0.0.1 \
        --port=8090 \
        --model=Melon/Meta-Llama-3-70B-Instruct-AutoAWQ-4bit \
        --tokenizer=meta-llama/Meta-Llama-3-70B-Instruct \
        --tensor-parallel-size=1 \
        --quantization awq \
        --dtype half
```