[Misc] Add SPDX-FileCopyrightText (#19100)

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

examples/offline_inference/audio_language.py

@@ -1,4 +1,5 @@
 # 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 audio language models.

examples/offline_inference/automatic_prefix_caching.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Demonstration script for Automatic Prefix Caching (APC) in vLLM.
 

examples/offline_inference/basic/basic.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, SamplingParams
 

examples/offline_inference/basic/chat.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, EngineArgs
 from vllm.utils import FlexibleArgumentParser

examples/offline_inference/basic/classify.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from argparse import Namespace
 

examples/offline_inference/basic/embed.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from argparse import Namespace
 

examples/offline_inference/basic/generate.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, EngineArgs
 from vllm.utils import FlexibleArgumentParser

examples/offline_inference/basic/score.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from argparse import Namespace
 

examples/offline_inference/batch_llm_inference.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This example shows how to use Ray Data for data parallel batch inference.
 

examples/offline_inference/chat_with_tools.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 # ruff: noqa
 import json

examples/offline_inference/context_extension.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, SamplingParams
 

examples/offline_inference/data_parallel.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Usage:
 Single node:

examples/offline_inference/disaggregated-prefill-v1/decode_example.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, SamplingParams
 from vllm.config import KVTransferConfig

examples/offline_inference/disaggregated-prefill-v1/prefill_example.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, SamplingParams
 from vllm.config import KVTransferConfig

examples/offline_inference/disaggregated_prefill.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This file demonstrates the example usage of disaggregated prefilling
 We will launch 2 vllm instances (GPU 0 for prefill and GPU 1 for decode),

examples/offline_inference/eagle.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import argparse
 import json
 import os

examples/offline_inference/embed_jina_embeddings_v3.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from argparse import Namespace
 

examples/offline_inference/embed_matryoshka_fy.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from argparse import Namespace
 

examples/offline_inference/encoder_decoder.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Demonstrate prompting of text-to-text
 encoder/decoder models, specifically BART

examples/offline_inference/encoder_decoder_multimodal.py

@@ -1,4 +1,5 @@
 # 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 explicit/implicit prompt format on enc-dec LMMs for text generation.

examples/offline_inference/llm_engine_example.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This file demonstrates using the `LLMEngine`
 for processing prompts with various sampling parameters.

examples/offline_inference/load_sharded_state.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Validates the loading of a model saved with the sharded_state format.
 This script demonstrates how to load a model that was previously saved

examples/offline_inference/lora_with_quantization_inference.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This example shows how to use LoRA with different quantization techniques
 for offline inference.

examples/offline_inference/metrics.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, SamplingParams
 from vllm.v1.metrics.reader import Counter, Gauge, Histogram, Vector

examples/offline_inference/mistral-small.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 # ruff: noqa
 import argparse

examples/offline_inference/mlpspeculator.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This file demonstrates the usage of text generation with an LLM model,
 comparing the performance with and without speculative decoding.

examples/offline_inference/multilora_inference.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This example shows how to use the multi-LoRA functionality
 for offline inference.

examples/offline_inference/neuron.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, SamplingParams
 

examples/offline_inference/neuron_eagle.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This example shows how to run offline inference with an EAGLE speculative
 decoding model on neuron. To use EAGLE speculative decoding, you must use

examples/offline_inference/neuron_int8_quantization.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import os
 

examples/offline_inference/neuron_multimodal.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import requests
 import torch
 from neuronx_distributed_inference.models.mllama.utils import add_instruct

examples/offline_inference/neuron_speculation.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This example shows how to run offline inference with a speculative
 decoding model on neuron.

examples/offline_inference/prefix_caching.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from vllm import LLM, SamplingParams
 from vllm.distributed import cleanup_dist_env_and_memory

examples/offline_inference/prithvi_geospatial_mae.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This is a demo script showing how to use the
 PrithviGeospatialMAE model with vLLM

examples/offline_inference/profiling.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import inspect
 import json

examples/offline_inference/profiling_tpu/profiling.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import dataclasses

examples/offline_inference/prompt_embed_inference.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Demonstrates how to generate prompt embeddings using
 Hugging Face Transformers  and use them as input to vLLM

examples/offline_inference/qwen2_5_omni/only_thinker.py

@@ -1,4 +1,5 @@
 # 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 Qwen2.5-Omni (thinker only).

examples/offline_inference/qwen_1m.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import os
 from urllib.request import urlopen
 

examples/offline_inference/reproducibility.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Demonstrates how to achieve reproducibility in vLLM.
 

examples/offline_inference/rlhf.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 a simple demonstration of RLHF with vLLM, inspired by
 the OpenRLHF framework https://github.com/OpenRLHF/OpenRLHF .

examples/offline_inference/rlhf_colocate.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 a simple demonstration to show how to co-locate
 vLLM worker with training actors on the same GPUs,

examples/offline_inference/rlhf_utils.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import torch
 
 

examples/offline_inference/save_sharded_state.py

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import os
 import time

examples/offline_inference/structured_outputs.py

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import os

examples/offline_inference/vision_language.py

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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

@@ -1,4 +1,5 @@
 # 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:
 

examples/online_serving/openai_chat_completion_structured_outputs_structural_tag.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from openai import OpenAI
 
 # This example demonstrates the `structural_tag` response format.

examples/online_serving/openai_chat_completion_structured_outputs_with_reasoning.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 An example shows how to generate structured outputs from reasoning models
 like DeepSeekR1. The thinking process will not be guided by the JSON

examples/online_serving/openai_chat_completion_tool_calls_with_reasoning.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 An example demonstrates how to use tool calling with reasoning models 
 like QwQ-32B. The reasoning_content will not be parsed by the tool 

examples/online_serving/openai_chat_completion_with_reasoning.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 An example shows how to generate chat completions from reasoning models
 like DeepSeekR1.

examples/online_serving/openai_chat_completion_with_reasoning_streaming.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 An example shows how to generate chat completions from reasoning models
 like DeepSeekR1.

examples/online_serving/openai_chat_embedding_client_for_multimodal.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import base64

examples/online_serving/openai_classification_client.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import pprint

examples/online_serving/openai_completion_client.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 

examples/online_serving/openai_cross_encoder_score.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Example online usage of Score API.
 

examples/online_serving/openai_embedding_client.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from openai import OpenAI
 

examples/online_serving/openai_embedding_matryoshka_fy.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Example Python client for embedding API dimensions using vLLM API server
 NOTE:
     start a supported Matryoshka Embeddings model server with `vllm serve`, e.g.

examples/online_serving/openai_pooling_client.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Example online usage of Pooling API.
 

examples/online_serving/openai_transcription_client.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import asyncio
 import json
 

examples/online_serving/opentelemetry/dummy_client.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import requests
 from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter

examples/online_serving/prompt_embed_inference_with_openai_client.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 vLLM OpenAI-Compatible Client with Prompt Embeddings
 

examples/online_serving/ray_serve_deepseek.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Example to deploy DeepSeek R1 or V3 with Ray Serve LLM.
 See more details at:

examples/online_serving/retrieval_augmented_generation_with_langchain.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Retrieval Augmented Generation (RAG) Implementation with Langchain
 ==================================================================

examples/online_serving/retrieval_augmented_generation_with_llamaindex.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 RAG (Retrieval Augmented Generation) Implementation with LlamaIndex
 ================================================================

examples/online_serving/streamlit_openai_chatbot_webserver.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 vLLM Chat Assistant - A Streamlit Web Interface
 

examples/online_serving/utils.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from openai import APIConnectionError, OpenAI
 from openai.pagination import SyncPage
 from openai.types.model import Model

examples/others/lmcache/cpu_offload_lmcache.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This file demonstrates the example usage of cpu offloading
 with LMCache in vLLM v1 or v0.

examples/others/lmcache/disagg_prefill_lmcache_v0.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This file demonstrates the example usage of disaggregated prefilling
 with LMCache.

examples/others/lmcache/disagg_prefill_lmcache_v1/disagg_proxy_server.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import os

examples/others/lmcache/kv_cache_sharing_lmcache_v1.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 This file demonstrates the example usage of remote KV cache sharing
 with LMCache.

examples/others/tensorize_vllm_model.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import argparse
 import dataclasses