[Misc] Add SPDX-FileCopyrightText (#20428)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

tests/v1/tpu/test_tpu_qkv_linear.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import tempfile
 
 import numpy as np

tools/check_pickle_imports.py

 #!/usr/bin/env python3
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import os
 import sys
 

tools/check_spdx_header.py

@@ -2,51 +2,146 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import sys
+from enum import Enum
 
-SPDX_HEADER = (
+
+class SPDXStatus(Enum):
+    """SPDX header status enumeration"""
+    EMPTY = "empty"  # empty __init__.py
+    COMPLETE = "complete"
+    MISSING_LICENSE = "missing_license"  # Only has copyright line
+    MISSING_COPYRIGHT = "missing_copyright"  # Only has license line
+    MISSING_BOTH = "missing_both"  # Completely missing
+
+
+FULL_SPDX_HEADER = (
     "# SPDX-License-Identifier: Apache-2.0\n"
     "# SPDX-FileCopyrightText: Copyright contributors to the vLLM project")
-SPDX_HEADER_PREFIX = "# SPDX-License-Identifier:"
 
+LICENSE_LINE = "# SPDX-License-Identifier: Apache-2.0"
+COPYRIGHT_LINE = "# SPDX-FileCopyrightText: Copyright contributors to the vLLM project"  # noqa: E501
 
-def check_spdx_header(file_path):
-    with open(file_path, encoding='UTF-8') as file:
+
+def check_spdx_header_status(file_path):
+    """Check SPDX header status of the file"""
+    with open(file_path, encoding="UTF-8") as file:
         lines = file.readlines()
         if not lines:
-            # Empty file like __init__.py
-            return True
-        for line in lines:
-            if line.strip().startswith(SPDX_HEADER_PREFIX):
-                return True
-    return False
+            # Empty file
+            return SPDXStatus.EMPTY
+
+        # Skip shebang line
+        start_idx = 0
+        if lines and lines[0].startswith("#!"):
+            start_idx = 1
 
+        has_license = False
+        has_copyright = False
 
-def add_header(file_path):
-    with open(file_path, 'r+', encoding='UTF-8') as file:
+        # Check all lines for SPDX headers (not just the first two)
+        for i in range(start_idx, len(lines)):
+            line = lines[i].strip()
+            if line == LICENSE_LINE:
+                has_license = True
+            elif line == COPYRIGHT_LINE:
+                has_copyright = True
+
+        # Determine status based on what we found
+        if has_license and has_copyright:
+            return SPDXStatus.COMPLETE
+        elif has_license and not has_copyright:
+            # Only has license line
+            return SPDXStatus.MISSING_COPYRIGHT
+            # Only has copyright line
+        elif not has_license and has_copyright:
+            return SPDXStatus.MISSING_LICENSE
+        else:
+            # Completely missing both lines
+            return SPDXStatus.MISSING_BOTH
+
+
+def add_header(file_path, status):
+    """Add or supplement SPDX header based on status"""
+    with open(file_path, "r+", encoding="UTF-8") as file:
         lines = file.readlines()
         file.seek(0, 0)
-        if lines and lines[0].startswith("#!"):
-            file.write(lines[0])
-            file.write(SPDX_HEADER + '\n')
-            file.writelines(lines[1:])
-        else:
-            file.write(SPDX_HEADER + '\n')
+        file.truncate()
+
+        if status == SPDXStatus.MISSING_BOTH:
+            # Completely missing, add complete header
+            if lines and lines[0].startswith("#!"):
+                # Preserve shebang line
+                file.write(lines[0])
+                file.write(FULL_SPDX_HEADER + "\n")
+                file.writelines(lines[1:])
+            else:
+                # Add header directly
+                file.write(FULL_SPDX_HEADER + "\n")
+                file.writelines(lines)
+
+        elif status == SPDXStatus.MISSING_COPYRIGHT:
+            # Only has license line, need to add copyright line
+            # Find the license line and add copyright line after it
+            for i, line in enumerate(lines):
+                if line.strip() == LICENSE_LINE:
+                    # Insert copyright line after license line
+                    lines.insert(
+                        i + 1,
+                        f"{COPYRIGHT_LINE}\n",
+                    )
+                    break
+
+            file.writelines(lines)
+
+        elif status == SPDXStatus.MISSING_LICENSE:
+            # Only has copyright line, need to add license line
+            # Find the copyright line and add license line before it
+            for i, line in enumerate(lines):
+                if line.strip() == COPYRIGHT_LINE:
+                    # Insert license line before copyright line
+                    lines.insert(i, f"{LICENSE_LINE}\n")
+                    break
             file.writelines(lines)
 
 
 def main():
-    files_with_missing_header = []
+    """Main function"""
+    files_missing_both = []
+    files_missing_copyright = []
+    files_missing_license = []
+
     for file_path in sys.argv[1:]:
-        if not check_spdx_header(file_path):
-            files_with_missing_header.append(file_path)
+        status = check_spdx_header_status(file_path)
 
-    if files_with_missing_header:
+        if status == SPDXStatus.MISSING_BOTH:
+            files_missing_both.append(file_path)
+        elif status == SPDXStatus.MISSING_COPYRIGHT:
+            files_missing_copyright.append(file_path)
+        elif status == SPDXStatus.MISSING_LICENSE:
+            files_missing_license.append(file_path)
+        else:
+            continue
+
+    # Collect all files that need fixing
+    all_files_to_fix = (files_missing_both + files_missing_copyright +
+                        files_missing_license)
+    if all_files_to_fix:
         print("The following files are missing the SPDX header:")
-        for file_path in files_with_missing_header:
-            print(f"  {file_path}")
-            add_header(file_path)
+        if files_missing_both:
+            for file_path in files_missing_both:
+                print(f"  {file_path}")
+                add_header(file_path, SPDXStatus.MISSING_BOTH)
+
+        if files_missing_copyright:
+            for file_path in files_missing_copyright:
+                print(f"  {file_path}")
+                add_header(file_path, SPDXStatus.MISSING_COPYRIGHT)
+        if files_missing_license:
+            for file_path in files_missing_license:
+                print(f"  {file_path}")
+                add_header(file_path, SPDXStatus.MISSING_LICENSE)
 
-    sys.exit(1 if files_with_missing_header else 0)
+    sys.exit(1 if all_files_to_fix else 0)
 
 
 if __name__ == "__main__":

vllm/compilation/fusion_attn.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import torch
 import torch._inductor.pattern_matcher as pm

vllm/distributed/eplb/__init__.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 '''
 Expert parallelism load balancer (EPLB).
 '''

vllm/distributed/eplb/eplb_state.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Expert parallelism load balancer (EPLB) metrics and states.
 

vllm/distributed/eplb/rebalance_algo.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Expert parallelism load balancer (EPLB) for vLLM.
 

vllm/distributed/eplb/rebalance_execute.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 The actual execution of the rearrangement.
 

vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py

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

vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py

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

vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py

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

vllm/distributed/tpu_distributed_utils.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from collections import OrderedDict
 from typing import Optional
 

vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 # ruff: noqa
 import json
 from collections.abc import Sequence

vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py

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

vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py

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

vllm/model_executor/layers/fused_moe/cpu_fused_moe.py

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

vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py

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

vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py

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

vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py

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

vllm/model_executor/layers/quantization/deepgemm.py

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