vLLM setup

minimal-vllm.sh

# Start vLLM OpenAI compatible server
docker run --runtime nvidia --gpus all \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HUGGING_FACE_HUB_TOKEN=<secret>" \
    -p 8000:8000 \
    --ipc=host \
    vllm/vllm-openai:latest \
    --api-key your-secret-key \
    --tokenizer-mode "mistral" \
    --model mistralai/Mistral-Small-24B-Instruct-2501
    
# Test query    
curl http://localhost:8000/v1/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your-secret-key" \
-d '{
    "model": "mistralai/Mistral-Small-24B-Instruct-2501",
    "prompt": "Raconte moi une histoire sur l exploration spatiale",
    "max_tokens": 128,
    "temperature": 0.7
}'