llm 2 vllm 1 text-generation-inference 1 sglang 1 ollama 1 modelscope 1 llamacpp 1 kubernetes 1 inference 1 huggingface 1 python 1 multimodal 1 model-serving 1 model-inference-service 1 mlops 1 ml-engineering 1 machine-learning 1 llmops 1 llm-serving 1 llm-inference 1 generative-ai 1 deep-learning 1 ai-inference 1