[Misc] Add SPDX-FileCopyrightText (#19100)

Signed-off-by: simon-mo <simon.mo@hey.com>

examples/offline_inference/save_sharded_state.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Saves each worker's model state dict directly to a checkpoint, which enables a
 fast load path for large tensor-parallel models where each worker only needs to

examples/offline_inference/simple_profiling.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import os
 import time

examples/offline_inference/structured_outputs.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This file demonstrates the example usage of guided decoding
 to generate structured outputs using vLLM. It shows how to apply

examples/offline_inference/torchrun_example.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 experimental support for tensor-parallel inference with torchrun,
 see https://github.com/vllm-project/vllm/issues/11400 for

examples/offline_inference/tpu.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import os

examples/offline_inference/vision_language.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This example shows how to use vLLM for running offline inference with
 the correct prompt format on vision language models for text generation.

examples/offline_inference/vision_language_embedding.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This example shows how to use vLLM for running offline inference with
 the correct prompt format on vision language models for multimodal embedding.

examples/offline_inference/vision_language_multi_image.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This example shows how to use vLLM for running offline inference with
 multi-image input on vision language models for text generation,

examples/online_serving/api_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Example Python client for `vllm.entrypoints.api_server`
 Start the demo server:
     python -m vllm.entrypoints.api_server --model <model_name>

examples/online_serving/cohere_rerank_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Example of using the OpenAI entrypoint's rerank API which is compatible with
 the Cohere SDK: https://github.com/cohere-ai/cohere-python

examples/online_serving/disaggregated_serving/disagg_proxy_demo.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This file provides a disaggregated prefilling proxy demo to demonstrate an
 example usage of XpYd disaggregated prefilling.

examples/online_serving/gradio_openai_chatbot_webserver.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Example for starting a Gradio OpenAI Chatbot Webserver
 Start vLLM API server:
     vllm serve meta-llama/Llama-2-7b-chat-hf

examples/online_serving/gradio_webserver.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Example for starting a Gradio Webserver
 Start vLLM API server:
     python -m vllm.entrypoints.api_server \

examples/online_serving/jinaai_rerank_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Example of using the OpenAI entrypoint's rerank API which is compatible with
 Jina and Cohere https://jina.ai/reranker

examples/online_serving/kv_events_subscriber.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from typing import Any, Optional, Union
 
 import msgspec

examples/online_serving/openai_chat_completion_client.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Example Python client for OpenAI Chat Completion using vLLM API server
 NOTE: start a supported chat completion model server with `vllm serve`, e.g.
     vllm serve meta-llama/Llama-2-7b-chat-hf

examples/online_serving/openai_chat_completion_client_for_multimodal.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """An example showing how to use vLLM to serve multimodal models
 and run online serving with OpenAI client.
 

examples/online_serving/openai_chat_completion_client_with_tools.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Set up this example by starting a vLLM OpenAI-compatible server with tool call
 options enabled. For example:

examples/online_serving/openai_chat_completion_client_with_tools_required.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 To run this example, you can start the vLLM server
 without any specific flags:

examples/online_serving/openai_chat_completion_structured_outputs.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 To run this example, you need to start the vLLM server: