Merge tag 'v0.18.1rc0' into v0.18.1rc0-ori

tests/entrypoints/openai/test_tensorizer_entrypoint.py → tests/entrypoints/openai/completion/test_tensorizer_entrypoint.py

@@ -9,6 +9,7 @@ import pytest
 import pytest_asyncio
 import torch.cuda
 
+from tests.utils import RemoteOpenAIServer
 from vllm.engine.arg_utils import EngineArgs
 from vllm.model_executor.model_loader.tensorizer import (
     TensorizerConfig,
@@ -17,8 +18,6 @@ from vllm.model_executor.model_loader.tensorizer import (
 )
 from vllm.platforms import current_platform
 
-from ...utils import RemoteOpenAIServer
-
 MODEL_NAME = "unsloth/llama-3.2-1b-Instruct"
 LORA_PATH = "davzoku/finqa_adapter_1b"
 

tests/entrypoints/openai/test_token_in_token_out.py → tests/entrypoints/openai/completion/test_token_in_token_out.py

@@ -6,11 +6,10 @@ import tempfile
 
 import pytest
 
+from tests.utils import RemoteOpenAIServer
 from vllm.model_executor.model_loader.weight_utils import download_weights_from_hf
 from vllm.tokenizers import get_tokenizer
 
-from ...utils import RemoteOpenAIServer
-
 MODEL_NAME = "Qwen/Qwen3-0.6B"
 MODEL_PATH = os.path.join(tempfile.gettempdir(), "qwen3_06b")
 

tests/entrypoints/openai/correctness/test_transcription_api_correctness.py

@@ -19,8 +19,10 @@ import soundfile
 import torch
 from datasets import load_dataset
 from evaluate import load
-from transformers import AutoTokenizer
 
+from vllm.tokenizers import get_tokenizer
+
+from ....models.registry import HF_EXAMPLE_MODELS
 from ....utils import RemoteOpenAIServer
 
 
@@ -64,8 +66,12 @@ async def bound_transcribe(sem, client, tokenizer, audio, reference):
 async def process_dataset(model, client, data, concurrent_request):
     sem = asyncio.Semaphore(concurrent_request)
 
-    # Load tokenizer once outside the loop
-    tokenizer = AutoTokenizer.from_pretrained(model)
+    model_info = HF_EXAMPLE_MODELS.find_hf_info(model)
+    tokenizer = get_tokenizer(
+        model,
+        tokenizer_mode=model_info.tokenizer_mode,
+        trust_remote_code=model_info.trust_remote_code,
+    )
 
     # Warmup call as the first `librosa.load` server-side is quite slow.
     audio, sr = data[0]["audio"]["array"], data[0]["audio"]["sampling_rate"]
@@ -144,20 +150,35 @@ def run_evaluation(
 
 
 # alternatives "openai/whisper-large-v2", "openai/whisper-large-v3-turbo"..
-@pytest.mark.parametrize("model_name", ["openai/whisper-large-v3"])
+# NOTE: Expected WER measured with equivalent hf.transformers args:
+# whisper-large-v3 + esb-datasets-earnings22-validation-tiny-filtered.
+@pytest.mark.parametrize(
+    "model_config",
+    [
+        ("openai/whisper-large-v3", 12.744980),
+        # TODO (ekagra): add HF ckpt after asr release
+        # ("/host/engines/vllm/audio/2b-release", 11.73),
+    ],
+)
 # Original dataset is 20GB+ in size, hence we use a pre-filtered slice.
 @pytest.mark.parametrize(
     "dataset_repo", ["D4nt3/esb-datasets-earnings22-validation-tiny-filtered"]
 )
-# NOTE: Expected WER measured with equivalent hf.transformers args:
-# whisper-large-v3 + esb-datasets-earnings22-validation-tiny-filtered.
-@pytest.mark.parametrize("expected_wer", [12.744980])
 def test_wer_correctness(
-    model_name, dataset_repo, expected_wer, n_examples=-1, max_concurrent_request=None
+    model_config, dataset_repo, n_examples=-1, max_concurrent_request=None
 ):
+    model_name, expected_wer = model_config
+    model_info = HF_EXAMPLE_MODELS.find_hf_info(model_name)
     # TODO refactor to use `ASRDataset`
+    server_args = [
+        "--enforce-eager",
+        f"--tokenizer_mode={model_info.tokenizer_mode}",
+    ]
+    if model_info.trust_remote_code:
+        server_args.append("--trust-remote-code")
     with RemoteOpenAIServer(
-        model_name, ["--enforce-eager"], max_wait_seconds=480
+        model_name,
+        server_args,
     ) as remote_server:
         dataset = load_hf_dataset(dataset_repo)
 
@@ -167,7 +188,14 @@ def test_wer_correctness(
 
         client = remote_server.get_async_client()
         wer = run_evaluation(
-            model_name, client, dataset, max_concurrent_request, n_examples
+            model_name,
+            client,
+            dataset,
+            max_concurrent_request,
+            n_examples,
         )
+
+        print(f"Expected WER: {expected_wer}, Actual WER: {wer}")
+
         if expected_wer:
             torch.testing.assert_close(wer, expected_wer, atol=1e-1, rtol=1e-2)

tests/entrypoints/openai/test_models.py → tests/entrypoints/openai/models/test_models.py

@@ -5,7 +5,7 @@ import openai  # use the official client for correctness check
 import pytest
 import pytest_asyncio
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 # any model with a chat template should work here
 MODEL_NAME = "Qwen/Qwen3-0.6B"

tests/entrypoints/openai/test_realtime_validation.py → tests/entrypoints/openai/realtime/test_realtime_validation.py

@@ -2,20 +2,19 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import asyncio
-import base64
 import json
 import warnings
 
 import librosa
 import numpy as np
+import pybase64 as base64
 import pytest
 import websockets
 
+from tests.entrypoints.openai.conftest import add_attention_backend
+from tests.utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
 from vllm.assets.audio import AudioAsset
 
-from ...utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
-from .conftest import add_attention_backend
-
 MISTRAL_FORMAT_ARGS = [
     "--tokenizer_mode",
     "mistral",

tests/entrypoints/openai/responses/conftest.py

@@ -8,6 +8,9 @@ from collections.abc import Callable
 from typing import Any
 
 import pytest
+import pytest_asyncio
+
+from tests.utils import RemoteOpenAIServer
 
 logger = logging.getLogger(__name__)
 
@@ -361,3 +364,38 @@ def log_response_diagnostics(
     )
 
     return diagnostics
+
+
+@pytest.fixture(scope="module")
+def default_server_args():
+    return [
+        "--max-model-len",
+        "18192",
+        "--enforce-eager",  # For faster startup.
+        "--enable-auto-tool-choice",
+        "--structured-outputs-config.backend",
+        "xgrammar",
+        "--tool-call-parser",
+        "hermes",
+        "--reasoning-parser",
+        "qwen3",
+    ]
+
+
+@pytest.fixture(scope="module")
+def server_with_store(default_server_args):
+    with RemoteOpenAIServer(
+        "Qwen/Qwen3-1.7B",
+        default_server_args,
+        env_dict={
+            "VLLM_ENABLE_RESPONSES_API_STORE": "1",
+            "VLLM_SERVER_DEV_MODE": "1",
+        },
+    ) as remote_server:
+        yield remote_server
+
+
+@pytest_asyncio.fixture
+async def client(server_with_store):
+    async with server_with_store.get_async_client() as async_client:
+        yield async_client

tests/v1/entrypoints/openai/serving_responses/test_function_call.py → tests/entrypoints/openai/responses/test_function_call.py

@@ -118,7 +118,6 @@ async def test_function_tool_use(
         tool_choice=tool_choice,
         temperature=0.0,
     )
-
     assert len(response.output) >= 1
     tool_call = None
     reasoning = None
@@ -127,11 +126,43 @@ async def test_function_tool_use(
             tool_call = out
         if out.type == "reasoning":
             reasoning = out
-    assert tool_call is not None
-    assert tool_call.type == "function_call"
-    assert json.loads(tool_call.arguments) is not None
-    assert reasoning is not None
-    assert reasoning.type == "reasoning"
+    if response.incomplete_details is None:
+        assert tool_call is not None
+        assert tool_call.type == "function_call"
+        assert json.loads(tool_call.arguments) is not None
+        assert reasoning is not None
+        assert reasoning.type == "reasoning"
+    else:
+        print(response.model_dump_json(indent=2))
+        assert response.incomplete_details.reason == "max_output_tokens"
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("model_name", [MODEL_NAME])
+async def test_max_tokens_with_tool_choice_required(
+    client: openai.AsyncOpenAI, model_name: str
+):
+    prompt = [
+        {
+            "role": "user",
+            "content": "Can you tell me what the current weather is in Berlin and the "
+            "forecast for the next 5 days, in fahrenheit?",
+        },
+    ]
+    response = await client.responses.create(
+        model=model_name,
+        input=prompt,
+        tools=tools,
+        tool_choice="required",
+        max_output_tokens=10,
+    )
+    assert len(response.output) >= 1
+    for out in response.output:
+        # When `tool_choice="required"` and the tokens of `tools`
+        # exceed `max_output_tokens`,`function_call` should be empty.
+        # This behavior should be consistent with OpenAI
+        assert out.type != "function_call"
+    assert response.incomplete_details.reason == "max_output_tokens"
 
 
 @pytest.mark.asyncio

tests/entrypoints/openai/responses/test_harmony.py

@@ -16,7 +16,8 @@ import requests
 from openai import InternalServerError, NotFoundError, OpenAI
 from openai_harmony import Message
 
-from ....utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
+
 from .conftest import (
     BASE_TEST_ENV,
     events_contain_type,

tests/entrypoints/openai/responses/test_mcp_tools.py

@@ -9,9 +9,9 @@ import pytest_asyncio
 from openai import OpenAI
 from openai_harmony import ToolDescription, ToolNamespaceConfig
 
+from tests.utils import RemoteOpenAIServer
 from vllm.entrypoints.mcp.tool_server import MCPToolServer
 
-from ....utils import RemoteOpenAIServer
 from .conftest import (
     BASE_TEST_ENV,
     events_contain_type,
@@ -42,7 +42,7 @@ class TestMCPToolServerUnit:
     Note: The wildcard "*" is normalized to None by
     _extract_allowed_tools_from_mcp_requests before reaching this layer,
     so we only test None and specific tool filtering here.
-    See test_serving_responses.py for "*" normalization tests.
+    See responses/test_serving_responses.py for "*" normalization tests.
     """
 
     def test_get_tool_description(self):

tests/entrypoints/openai/responses/test_parsable_context.py

@@ -9,7 +9,8 @@ import pytest
 import pytest_asyncio
 from openai import OpenAI
 
-from ....utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
+
 from .conftest import (
     BASE_TEST_ENV,
     has_output_type,

tests/entrypoints/openai/test_serving_responses.py → tests/entrypoints/openai/responses/test_serving_responses.py

@@ -159,6 +159,7 @@ class TestInitializeToolSessions:
         instance = OpenAIServingResponses(
             engine_client=engine_client,
             models=models,
+            openai_serving_render=MagicMock(),
             request_logger=None,
             chat_template=None,
             chat_template_content_format="auto",
@@ -245,6 +246,7 @@ class TestValidateGeneratorInput:
         instance = OpenAIServingResponses(
             engine_client=engine_client,
             models=models,
+            openai_serving_render=MagicMock(),
             request_logger=None,
             chat_template=None,
             chat_template_content_format="auto",
@@ -308,6 +310,7 @@ async def test_reasoning_tokens_counted_for_text_reasoning_model(monkeypatch):
     serving = OpenAIServingResponses(
         engine_client=engine_client,
         models=models,
+        openai_serving_render=MagicMock(),
         request_logger=None,
         chat_template=None,
         chat_template_content_format="auto",
@@ -607,6 +610,7 @@ def _make_serving_instance_with_reasoning():
     serving = OpenAIServingResponses(
         engine_client=engine_client,
         models=models,
+        openai_serving_render=MagicMock(),
         request_logger=None,
         chat_template=None,
         chat_template_content_format="auto",

tests/entrypoints/openai/responses/test_simple.py

@@ -5,7 +5,8 @@ import pytest
 import pytest_asyncio
 from openai import OpenAI
 
-from ....utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
+
 from .conftest import validate_streaming_event_stack
 
 MODEL_NAME = "Qwen/Qwen3-8B"