# Offline Inference Offline inference examples demonstrate how to use vLLM in an offline setting, where the model is queried for predictions in batches. :::{toctree} :caption: Examples :maxdepth: 1 aqlm_example arctic audio_language basic basic_with_model_default_sampling chat chat_with_tools classification cli cpu_offload distributed embedding encoder_decoder florence2_inference gguf_inference llm_engine_example lora_with_quantization_inference mlpspeculator multilora_inference neuron neuron_int8_quantization openai pixtral prefix_caching profiling profiling_tpu rlhf save_sharded_state scoring simple_profiling structured_outputs torchrun_example tpu vision_language vision_language_embedding vision_language_multi_image whisper :::