Mark files that have been modified by Neural Magic (#70)

SUMMARY:
for Apache 4(b) -- "You must cause any modified files to carry prominent
notices stating that You changed the files"
https://www.apache.org/licenses/LICENSE-2.0 

TEST PLAN:
GHA

.gitignore

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

benchmarks/backend_request_func.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 import json
 import os
 import time

csrc/ops.h

@@ -1,3 +1,5 @@
+// This file has been modified by Neural Magic
+
 #pragma once
 
 #include <torch/extension.h>

csrc/pybind.cpp

@@ -1,3 +1,5 @@
+// This file has been modified by Neural Magic
+
 #include "cache.h"
 #include "cuda_utils.h"
 #include "ops.h"

requirements-dev.txt

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 # formatting
 yapf==0.32.0
 toml==0.10.2

setup.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 import contextlib
 import io
 import os

tests/conftest.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 import os
 from typing import List, Optional, Tuple
 

tests/distributed/test_custom_all_reduce.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 import random
 
 import os

tests/entrypoints/test_openai_server.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 import os
 import subprocess
 import time

tests/models/test_mistral.py

@@ -1,3 +1,4 @@
+# This file has been modified by Neural Magic
 """Compare the outputs of HF and vLLM for Mistral models using greedy sampling.
 
 Run `pytest tests/models/test_mistral.py --forked`.

tests/models/test_models.py

@@ -1,3 +1,4 @@
+# This file has been modified by Neural Magic
 """Compare the outputs of HF and vLLM when using greedy sampling.
 
 Run `pytest tests/models/test_models.py --forked`.

vllm/config.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 from typing import Optional, Union, ClassVar
 from dataclasses import dataclass
 import os

vllm/engine/arg_utils.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 import argparse
 import dataclasses
 from dataclasses import dataclass

vllm/engine/llm_engine.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 import copy
 from collections import defaultdict
 import os

vllm/entrypoints/llm.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 from typing import List, Optional, Union
 
 from tqdm import tqdm

vllm/model_executor/layers/linear.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 from abc import ABC, abstractmethod
 from typing import Any, Dict, List, Optional
 

vllm/model_executor/layers/quantization/__init__.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 from typing import Type
 
 from vllm.model_executor.layers.quantization.base_config import QuantizationConfig

vllm/model_executor/model_loader.py

@@ -1,3 +1,4 @@
+# This file has been modified by Neural Magic
 """Utilities for selecting and loading models."""
 import contextlib
 from typing import Optional, Type

vllm/model_executor/weight_utils.py

@@ -1,3 +1,4 @@
+# This file has been modified by Neural Magic
 """Utilities for downloading and initializing model weights."""
 import filelock
 import glob

vllm/test_utils.py

@@ -1,3 +1,5 @@
+# This file has been modified by Neural Magic
+
 import ray
 
 from vllm.config import ParallelConfig