Merge tag 'v0.7.2' into v0.7.2-dev

tests/entrypoints/openai/test_oot_registration.py

+# SPDX-License-Identifier: Apache-2.0
+
 import os
 from ...utils import VLLM_PATH, RemoteOpenAIServer, models_path_prefix, envs
 

tests/entrypoints/openai/test_pooling.py

+# SPDX-License-Identifier: Apache-2.0
+
 import base64
 
 import numpy as np

tests/entrypoints/openai/test_prompt_validation.py

+# SPDX-License-Identifier: Apache-2.0
+
 # imports for guided decoding tests
 import re
 import os

tests/entrypoints/openai/test_rerank.py

+# SPDX-License-Identifier: Apache-2.0
+
 import pytest
 import requests
 

tests/entrypoints/openai/test_return_tokens_as_ids.py

+# SPDX-License-Identifier: Apache-2.0
+
 # Separate these tests out from test_completion and test_chat, because they
 # require launching a second server with a different flag. Running both servers
 # at the same time on a single node will OOM.

tests/entrypoints/openai/test_root_path.py

+# SPDX-License-Identifier: Apache-2.0
+
 import contextlib
 import os
 from typing import Any, List, NamedTuple

tests/entrypoints/openai/test_run_batch.py

+# SPDX-License-Identifier: Apache-2.0
+
 import json
 import subprocess
 import sys

tests/entrypoints/openai/test_score.py

+# SPDX-License-Identifier: Apache-2.0
+
 import os
 import pytest
 import requests

tests/entrypoints/openai/test_serving_chat.py

+# SPDX-License-Identifier: Apache-2.0
+
 import asyncio
 from contextlib import suppress
 from dataclasses import dataclass

tests/entrypoints/openai/test_serving_models.py

+# SPDX-License-Identifier: Apache-2.0
+
 from http import HTTPStatus
 from unittest.mock import MagicMock
 

tests/entrypoints/openai/test_shutdown.py

+# SPDX-License-Identifier: Apache-2.0
+
 import openai
 import pytest
 

tests/entrypoints/openai/test_tokenization.py

+# SPDX-License-Identifier: Apache-2.0
+
 import pytest
 import os
 import pytest_asyncio

tests/entrypoints/openai/test_video.py

+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Dict, List
 
 import os

tests/entrypoints/openai/test_vision.py

+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Dict, List
 
 import openai

tests/entrypoints/openai/test_vision_embedding.py

+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Dict
 
 import os

tests/entrypoints/openai/tool_parsers/test_pythonic_tool_parser.py

+# SPDX-License-Identifier: Apache-2.0
+
 from typing import List
 from unittest.mock import MagicMock
 

tests/entrypoints/openai/tool_parsers/utils.py

+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Iterable, List, Tuple, Union
 
 from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,

tests/entrypoints/test_chat_utils.py

+# SPDX-License-Identifier: Apache-2.0
+
 import warnings
 from typing import Optional
 
@@ -761,7 +763,6 @@ def test_resolve_content_format_hf_defined(model, expected_format):
      ("template_falcon.jinja", "string"),
      ("template_inkbot.jinja", "string"),
      ("template_llava.jinja", "string"),
-     ("template_pixtral_hf.jinja", "openai"),
      ("template_vlm2vec.jinja", "openai"),
      ("tool_chat_template_granite_20b_fc.jinja", "string"),
      ("tool_chat_template_hermes.jinja", "string"),

tests/kernels/allclose_default.py

+# SPDX-License-Identifier: Apache-2.0
+
 import torch
 
 # Reference default values of atol and rtol are from

tests/kernels/conftest.py

+# SPDX-License-Identifier: Apache-2.0
+
 import pytest
 
 from vllm.utils import (create_kv_caches_with_random,