Running DeepSeek on HPC

commands.txt

# Loading and serving the model:

vllm serve /root/commonData/DeepSeek-R1 \
    --host 0.0.0.0 \
    --port 8000 \
    --enable-reasoning \
    --reasoning-parser deepseek_r1 \
    --tensor-parallel-size 8 \
    --load-format auto \
    --trust-remote-code \
    --served-model-name deepseek-ai/DeepSeek-R1
    
# Running inference:

curl "http://localhost:8000/v1/chat/completions" \
    -H "Content-Type: application/json" \
    -d '{ 
        "model": "deepseek-ai/DeepSeek-R1",
        "messages": [{
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a short description of a hypothetical gray car"
        }
    ]}'