[Refactor] Relocate completion and chat completion tests (#37125)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

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

@@ -14,7 +14,7 @@ import torch
 from openai import BadRequestError
 from transformers import AutoConfig
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 # any model with a chat template should work here
 MODEL_NAME = "facebook/opt-125m"

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

@@ -11,11 +11,10 @@ import pytest
 import regex as re
 import torch
 
+from tests.utils import RemoteOpenAIServer
 from vllm.config import ModelConfig
 from vllm.renderers.embed_utils import safe_load_prompt_embeds
 
-from ...utils import RemoteOpenAIServer
-
 
 @pytest.mark.asyncio
 async def test_empty_prompt():

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")