Examples
=================================

.. toctree::
   :maxdepth: 1
   :caption: Scripts

   api_client
   aqlm_example
   cpu_offload
   florence2_inference
   gguf_inference
   gradio_openai_chatbot_webserver
   gradio_webserver
   llm_engine_example
   lora_with_quantization_inference
   multilora_inference
   offline_chat_with_tools
   offline_inference
   offline_inference_arctic
   offline_inference_audio_language
   offline_inference_chat
   offline_inference_distributed
   offline_inference_embedding
   offline_inference_encoder_decoder
   offline_inference_mlpspeculator
   offline_inference_neuron
   offline_inference_neuron_int8_quantization
   offline_inference_pixtral
   offline_inference_tpu
   offline_inference_vision_language
   offline_inference_vision_language_embedding
   offline_inference_vision_language_multi_image
   offline_inference_with_prefix
   offline_inference_with_profiler
   offline_profile
   openai_chat_completion_client
   openai_chat_completion_client_for_multimodal
   openai_chat_completion_client_with_tools
   openai_chat_embedding_client_for_multimodal
   openai_completion_client
   openai_embedding_client
   save_sharded_state
   tensorize_vllm_model