# Examples

```{toctree}
:maxdepth: 1
:caption: Scripts

api_client.md
aqlm_example.md
cpu_offload.md
florence2_inference.md
gguf_inference.md
gradio_openai_chatbot_webserver.md
gradio_webserver.md
llm_engine_example.md
lora_with_quantization_inference.md
multilora_inference.md
offline_chat_with_tools.md
offline_inference.md
offline_inference_arctic.md
offline_inference_audio_language.md
offline_inference_chat.md
offline_inference_classification.md
offline_inference_cli.md
offline_inference_distributed.md
offline_inference_embedding.md
offline_inference_encoder_decoder.md
offline_inference_mlpspeculator.md
offline_inference_neuron.md
offline_inference_neuron_int8_quantization.md
offline_inference_pixtral.md
offline_inference_scoring.md
offline_inference_structured_outputs.md
offline_inference_tpu.md
offline_inference_vision_language.md
offline_inference_vision_language_embedding.md
offline_inference_vision_language_multi_image.md
offline_inference_with_default_generation_config.md
offline_inference_with_prefix.md
offline_inference_with_profiler.md
offline_profile.md
openai_chat_completion_client.md
openai_chat_completion_client_for_multimodal.md
openai_chat_completion_client_with_tools.md
openai_chat_completion_structured_outputs.md
openai_chat_embedding_client_for_multimodal.md
openai_completion_client.md
openai_cross_encoder_score.md
openai_embedding_client.md
openai_pooling_client.md
save_sharded_state.md
tensorize_vllm_model.md
```