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

tests/entrypoints/llm/test_lazy_outlines.py

+# SPDX-License-Identifier: Apache-2.0
+
 import sys
 import os
 from contextlib import nullcontext

tests/entrypoints/llm/test_prompt_validation.py

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

tests/entrypoints/offline_mode/test_offline_mode.py

+# SPDX-License-Identifier: Apache-2.0
 """Tests for HF_HUB_OFFLINE mode"""
 import importlib
 import sys

tests/entrypoints/openai/reasoning_parsers/test_deepseekr1_reasoning_parser.py

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

tests/entrypoints/openai/reasoning_parsers/utils.py

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

tests/entrypoints/openai/test_accuracy.py

+# SPDX-License-Identifier: Apache-2.0
 """
 This file test accuracy of the vLLM server via LMEval.
 It uses local-completions, which interacts with vLLM

tests/entrypoints/openai/test_async_tokenization.py

+# SPDX-License-Identifier: Apache-2.0
+
 import asyncio
 import contextlib
 import random

tests/entrypoints/openai/test_audio.py

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

tests/entrypoints/openai/test_basic.py

+# SPDX-License-Identifier: Apache-2.0
+
 import asyncio
 from http import HTTPStatus
 from typing import List

tests/entrypoints/openai/test_chat.py

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

tests/entrypoints/openai/test_chat_echo.py

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

tests/entrypoints/openai/test_chat_template.py

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

tests/entrypoints/openai/test_chunked_prompt.py

+# SPDX-License-Identifier: Apache-2.0
+
 import os
 import openai  # use the official client for correctness check
 import pytest

tests/entrypoints/openai/test_cli_args.py

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

tests/entrypoints/openai/test_completion.py

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

tests/entrypoints/openai/test_embedding.py

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

tests/entrypoints/openai/test_encoder_decoder.py

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

tests/entrypoints/openai/test_lora_adapters.py

+# SPDX-License-Identifier: Apache-2.0
+
 import asyncio
 import json
 import shutil

tests/entrypoints/openai/test_metrics.py

+# SPDX-License-Identifier: Apache-2.0
+
 import subprocess
 import sys
 import tempfile
@@ -204,6 +206,7 @@ EXPECTED_METRICS_V1 = [
     "vllm:gpu_cache_usage_perc",
     "vllm:prompt_tokens_total",
     "vllm:generation_tokens_total",
+    "vllm:request_success_total",
     "vllm:request_prompt_tokens_sum",
     "vllm:request_prompt_tokens_bucket",
     "vllm:request_prompt_tokens_count",

tests/entrypoints/openai/test_models.py

+# SPDX-License-Identifier: Apache-2.0
+
 import openai  # use the official client for correctness check
 import pytest
 import os