[MISC] Fix import error for fused_moe

docs/source/getting_started/examples/api_client.rst

@@ -0,0 +1,8 @@
+API Client
+==========
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/api_client.py.
+
+.. literalinclude:: ../../../../examples/api_client.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/aqlm_example.rst

@@ -0,0 +1,8 @@
+Aqlm Example
+============
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/aqlm_example.py.
+
+.. literalinclude:: ../../../../examples/aqlm_example.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/cpu_offload.rst

@@ -0,0 +1,8 @@
+Cpu Offload
+===========
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/cpu_offload.py.
+
+.. literalinclude:: ../../../../examples/cpu_offload.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/examples_index.rst

@@ -0,0 +1,48 @@
+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_cli
+   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_structured_outputs
+   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_completion_structured_outputs
+   openai_chat_embedding_client_for_multimodal
+   openai_completion_client
+   openai_cross_encoder_score
+   openai_embedding_client
+   save_sharded_state
+   tensorize_vllm_model

docs/source/getting_started/examples/florence2_inference.rst

@@ -0,0 +1,8 @@
+Florence2 Inference
+===================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/florence2_inference.py.
+
+.. literalinclude:: ../../../../examples/florence2_inference.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/gguf_inference.rst

@@ -0,0 +1,8 @@
+Gguf Inference
+==============
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/gguf_inference.py.
+
+.. literalinclude:: ../../../../examples/gguf_inference.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/gradio_openai_chatbot_webserver.rst

@@ -0,0 +1,8 @@
+Gradio OpenAI Chatbot Webserver
+===============================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/gradio_openai_chatbot_webserver.py.
+
+.. literalinclude:: ../../../../examples/gradio_openai_chatbot_webserver.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/gradio_webserver.rst

@@ -0,0 +1,8 @@
+Gradio Webserver
+================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/gradio_webserver.py.
+
+.. literalinclude:: ../../../../examples/gradio_webserver.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/llm_engine_example.rst

@@ -0,0 +1,8 @@
+LLM Engine Example
+==================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/llm_engine_example.py.
+
+.. literalinclude:: ../../../../examples/llm_engine_example.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/lora_with_quantization_inference.rst

@@ -0,0 +1,8 @@
+Lora With Quantization Inference
+================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/lora_with_quantization_inference.py.
+
+.. literalinclude:: ../../../../examples/lora_with_quantization_inference.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/multilora_inference.rst

@@ -0,0 +1,8 @@
+MultiLoRA Inference
+===================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/multilora_inference.py.
+
+.. literalinclude:: ../../../../examples/multilora_inference.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_chat_with_tools.rst

@@ -0,0 +1,8 @@
+Offline Chat With Tools
+=======================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_chat_with_tools.py.
+
+.. literalinclude:: ../../../../examples/offline_chat_with_tools.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference.rst

@@ -0,0 +1,8 @@
+Offline Inference
+=================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference.py.
+
+.. literalinclude:: ../../../../examples/offline_inference.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_arctic.rst

@@ -0,0 +1,8 @@
+Offline Inference Arctic
+========================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_arctic.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_arctic.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_audio_language.rst

@@ -0,0 +1,8 @@
+Offline Inference Audio Language
+================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_audio_language.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_audio_language.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_chat.rst

@@ -0,0 +1,8 @@
+Offline Inference Chat
+======================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_chat.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_chat.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_cli.rst

@@ -0,0 +1,8 @@
+Offline Inference Cli
+=====================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_cli.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_cli.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_distributed.rst

@@ -0,0 +1,8 @@
+Offline Inference Distributed
+=============================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_distributed.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_distributed.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_embedding.rst

@@ -0,0 +1,8 @@
+Offline Inference Embedding
+===========================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_embedding.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_embedding.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_encoder_decoder.rst

@@ -0,0 +1,8 @@
+Offline Inference Encoder Decoder
+=================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_encoder_decoder.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_encoder_decoder.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_mlpspeculator.rst

@@ -0,0 +1,8 @@
+Offline Inference Mlpspeculator
+===============================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_mlpspeculator.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_mlpspeculator.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_neuron.rst

@@ -0,0 +1,8 @@
+Offline Inference Neuron
+========================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_neuron.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_neuron.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_neuron_int8_quantization.rst

@@ -0,0 +1,8 @@
+Offline Inference Neuron Int8 Quantization
+==========================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_neuron_int8_quantization.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_neuron_int8_quantization.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_pixtral.rst

@@ -0,0 +1,8 @@
+Offline Inference Pixtral
+=========================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_pixtral.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_pixtral.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_structured_outputs.rst

@@ -0,0 +1,8 @@
+Offline Inference Structured Outputs
+====================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_structured_outputs.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_structured_outputs.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_tpu.rst

@@ -0,0 +1,8 @@
+Offline Inference Tpu
+=====================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_tpu.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_tpu.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_vision_language.rst

@@ -0,0 +1,8 @@
+Offline Inference Vision Language
+=================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_vision_language.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_vision_language.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_vision_language_embedding.rst

@@ -0,0 +1,8 @@
+Offline Inference Vision Language Embedding
+===========================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_vision_language_embedding.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_vision_language_embedding.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_vision_language_multi_image.rst

@@ -0,0 +1,8 @@
+Offline Inference Vision Language Multi Image
+=============================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_vision_language_multi_image.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_vision_language_multi_image.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_with_prefix.rst

@@ -0,0 +1,8 @@
+Offline Inference With Prefix
+=============================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_with_prefix.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_with_prefix.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_inference_with_profiler.rst

@@ -0,0 +1,8 @@
+Offline Inference With Profiler
+===============================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_inference_with_profiler.py.
+
+.. literalinclude:: ../../../../examples/offline_inference_with_profiler.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/offline_profile.rst

@@ -0,0 +1,8 @@
+Offline Profile
+===============
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/offline_profile.py.
+
+.. literalinclude:: ../../../../examples/offline_profile.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/openai_chat_completion_client.rst

@@ -0,0 +1,8 @@
+OpenAI Chat Completion Client
+=============================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/openai_chat_completion_client.py.
+
+.. literalinclude:: ../../../../examples/openai_chat_completion_client.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/openai_chat_completion_client_for_multimodal.rst

@@ -0,0 +1,8 @@
+OpenAI Chat Completion Client For Multimodal
+============================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/openai_chat_completion_client_for_multimodal.py.
+
+.. literalinclude:: ../../../../examples/openai_chat_completion_client_for_multimodal.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/openai_chat_completion_client_with_tools.rst

@@ -0,0 +1,8 @@
+OpenAI Chat Completion Client With Tools
+========================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/openai_chat_completion_client_with_tools.py.
+
+.. literalinclude:: ../../../../examples/openai_chat_completion_client_with_tools.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/openai_chat_completion_structured_outputs.rst

@@ -0,0 +1,8 @@
+OpenAI Chat Completion Structured Outputs
+=========================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/openai_chat_completion_structured_outputs.py.
+
+.. literalinclude:: ../../../../examples/openai_chat_completion_structured_outputs.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/openai_chat_embedding_client_for_multimodal.rst

@@ -0,0 +1,8 @@
+OpenAI Chat Embedding Client For Multimodal
+===========================================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/openai_chat_embedding_client_for_multimodal.py.
+
+.. literalinclude:: ../../../../examples/openai_chat_embedding_client_for_multimodal.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/openai_completion_client.rst

@@ -0,0 +1,8 @@
+OpenAI Completion Client
+========================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/openai_completion_client.py.
+
+.. literalinclude:: ../../../../examples/openai_completion_client.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/openai_cross_encoder_score.rst

@@ -0,0 +1,8 @@
+OpenAI Cross Encoder Score
+==========================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/openai_cross_encoder_score.py.
+
+.. literalinclude:: ../../../../examples/openai_cross_encoder_score.py
+    :language: python
+    :linenos:

docs/source/getting_started/examples/openai_embedding_client.rst

@@ -0,0 +1,8 @@
+OpenAI Embedding Client
+=======================
+
+Source https://github.com/vllm-project/vllm/blob/main/examples/openai_embedding_client.py.
+
+.. literalinclude:: ../../../../examples/openai_embedding_client.py
+    :language: python
+    :linenos: