[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**

commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date:   Fri Jan 31 14:18:24 2025 -0500

    Add SPDX license headers to python source files
    
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
    also be easily used by tools to help manage license compliance.
    
The Linux Foundation runs license scans against the codebase to help
ensure
    we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
    
    More information can be found on the SPDX site:
    
    - https://spdx.dev/learn/handling-license-info/

Signed-off-by: Russell Bryant <rbryant@redhat.com>

commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date:   Fri Jan 31 14:36:32 2025 -0500

    Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>

---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>

examples/offline_inference/florence2_inference.py

+# SPDX-License-Identifier: Apache-2.0
 '''
 Demonstrate prompting of text-to-text
 encoder/decoder models, specifically Florence-2

examples/offline_inference/gguf_inference.py

+# SPDX-License-Identifier: Apache-2.0
+
 from huggingface_hub import hf_hub_download
 
 from vllm import LLM, SamplingParams

examples/offline_inference/llm_engine_example.py

+# SPDX-License-Identifier: Apache-2.0
+
 import argparse
 from typing import List, Tuple
 

examples/offline_inference/lora_with_quantization_inference.py

+# SPDX-License-Identifier: Apache-2.0
 """
 This example shows how to use LoRA with different quantization techniques
 for offline inference.

examples/offline_inference/mlpspeculator.py

+# SPDX-License-Identifier: Apache-2.0
+
 import gc
 import time
 from typing import List

examples/offline_inference/multilora_inference.py

+# SPDX-License-Identifier: Apache-2.0
 """
 This example shows how to use the multi-LoRA functionality
 for offline inference.

examples/offline_inference/neuron.py

+# SPDX-License-Identifier: Apache-2.0
+
 from vllm import LLM, SamplingParams
 
 # Sample prompts.

examples/offline_inference/neuron_int8_quantization.py

+# SPDX-License-Identifier: Apache-2.0
+
 import os
 
 from vllm import LLM, SamplingParams

examples/offline_inference/pixtral.py

+# SPDX-License-Identifier: Apache-2.0
+
 # ruff: noqa
 import argparse
 

examples/offline_inference/prefix_caching.py

+# SPDX-License-Identifier: Apache-2.0
+
 from vllm import LLM, SamplingParams
 from vllm.distributed import cleanup_dist_env_and_memory
 

examples/offline_inference/profiling.py

+# SPDX-License-Identifier: Apache-2.0
+
 import inspect
 import json
 import os

examples/offline_inference/profiling_tpu/profiling.py

+# SPDX-License-Identifier: Apache-2.0
+
 import argparse
 import dataclasses
 import os

examples/offline_inference/rlhf.py

+# SPDX-License-Identifier: Apache-2.0
 """
 a simple demonstration of RLHF with vLLM, inspired by
 the OpenRLHF framework https://github.com/OpenRLHF/OpenRLHF .

examples/offline_inference/save_sharded_state.py

+# SPDX-License-Identifier: Apache-2.0
 """
 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/scoring.py

+# SPDX-License-Identifier: Apache-2.0
+
 from vllm import LLM
 
 # Sample prompts.

examples/offline_inference/simple_profiling.py

+# SPDX-License-Identifier: Apache-2.0
+
 import os
 import time
 

examples/offline_inference/structured_outputs.py

+# SPDX-License-Identifier: Apache-2.0
+
 from enum import Enum
 
 from pydantic import BaseModel

examples/offline_inference/torchrun_example.py

+# SPDX-License-Identifier: Apache-2.0
 """
 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
+
 from vllm import LLM, SamplingParams
 
 prompts = [

examples/offline_inference/vision_language.py

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