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

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

.buildkite/scripts/hardware_ci/run-amd-test.sh

@@ -333,15 +333,15 @@ apply_rocm_test_overrides() {
   # --- Entrypoint ignores ---
   if [[ $cmds == *" entrypoints/openai "* ]]; then
     cmds=${cmds//" entrypoints/openai "/" entrypoints/openai \
-    --ignore=entrypoints/openai/test_audio.py \
+    --ignore=entrypoints/openai/chat_completion/test_audio.py \
-    --ignore=entrypoints/openai/test_shutdown.py \
+    --ignore=entrypoints/openai/completion/test_shutdown.py \
     --ignore=entrypoints/openai/test_completion.py \
     --ignore=entrypoints/openai/test_models.py \
     --ignore=entrypoints/openai/test_lora_adapters.py \
     --ignore=entrypoints/openai/test_return_tokens_as_ids.py \
-    --ignore=entrypoints/openai/test_root_path.py \
+    --ignore=entrypoints/openai/chat_completion/test_root_path.py \
     --ignore=entrypoints/openai/test_tokenization.py \
-    --ignore=entrypoints/openai/test_prompt_validation.py "}
+    --ignore=entrypoints/openai/completion/test_prompt_validation.py "}
   fi
 
   if [[ $cmds == *" entrypoints/llm "* ]]; then

.buildkite/test-amd.yaml

@@ -162,7 +162,7 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
 
 - label: Entrypoints Integration Test (API Server 2)
@@ -674,12 +674,12 @@ steps:
   - vllm/config/model.py
   - vllm/model_executor
   - tests/model_executor
-  - tests/entrypoints/openai/test_tensorizer_entrypoint.py
+  - tests/entrypoints/openai/completion/test_tensorizer_entrypoint.py
   commands:
     - apt-get update && apt-get install -y curl libsodium23
     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
     - pytest -v -s model_executor
-    - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
+    - pytest -v -s entrypoints/openai/completion/test_tensorizer_entrypoint.py
 
 - label: Benchmarks # 11min
   timeout_in_minutes: 20
@@ -1143,7 +1143,7 @@ steps:
   - pytest -v -s plugins_tests/test_scheduler_plugins.py
   - pip install -e ./plugins/vllm_add_dummy_model
   - pytest -v -s distributed/test_distributed_oot.py
-  - pytest -v -s entrypoints/openai/test_oot_registration.py
+  - pytest -v -s entrypoints/openai/chat_completion/test_oot_registration.py
   - pytest -v -s models/test_oot_registration.py
   - pytest -v -s plugins/lora_resolvers
 
@@ -1502,7 +1502,7 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
 
 - label: Entrypoints Integration Test (API Server 2)
@@ -2133,12 +2133,12 @@ steps:
   - vllm/config/model.py
   - vllm/model_executor
   - tests/model_executor
-  - tests/entrypoints/openai/test_tensorizer_entrypoint.py
+  - tests/entrypoints/openai/completion/test_tensorizer_entrypoint.py
   commands:
     - apt-get update && apt-get install -y curl libsodium23
     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
     - pytest -v -s model_executor
-    - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
+    - pytest -v -s entrypoints/openai/completion/test_tensorizer_entrypoint.py
 
 - label: Benchmarks # 11min
   timeout_in_minutes: 20
@@ -2735,7 +2735,7 @@ steps:
   - pytest -v -s plugins_tests/test_scheduler_plugins.py
   - pip install -e ./plugins/vllm_add_dummy_model
   - pytest -v -s distributed/test_distributed_oot.py
-  - pytest -v -s entrypoints/openai/test_oot_registration.py # it needs a clean process
+  - pytest -v -s entrypoints/openai/chat_completion/test_oot_registration.py # it needs a clean process
   - pytest -v -s models/test_oot_registration.py # it needs a clean process
   - pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins
 
@@ -3257,7 +3257,7 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
 
 - label: Entrypoints Integration Test (API Server 2)
@@ -3872,12 +3872,12 @@ steps:
   - vllm/config/model.py
   - vllm/model_executor
   - tests/model_executor
-  - tests/entrypoints/openai/test_tensorizer_entrypoint.py
+  - tests/entrypoints/openai/completion/test_tensorizer_entrypoint.py
   commands:
     - apt-get update && apt-get install -y curl libsodium23
     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
     - pytest -v -s model_executor
-    - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
+    - pytest -v -s entrypoints/openai/completion/test_tensorizer_entrypoint.py
 
 - label: Benchmarks # 11min
   timeout_in_minutes: 20
@@ -4508,7 +4508,7 @@ steps:
   - pytest -v -s plugins_tests/test_scheduler_plugins.py
   - pip install -e ./plugins/vllm_add_dummy_model
   - pytest -v -s distributed/test_distributed_oot.py
-  - pytest -v -s entrypoints/openai/test_oot_registration.py # it needs a clean process
+  - pytest -v -s entrypoints/openai/chat_completion/test_oot_registration.py # it needs a clean process
   - pytest -v -s models/test_oot_registration.py # it needs a clean process
   - pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins
 

.buildkite/test_areas/entrypoints.yaml

@@ -34,7 +34,7 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/  --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/  --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
   mirror:
     amd:

.buildkite/test_areas/model_executor.yaml

@@ -9,9 +9,9 @@ steps:
   - vllm/config/model.py
   - vllm/model_executor
   - tests/model_executor
-  - tests/entrypoints/openai/test_tensorizer_entrypoint.py
+  - tests/entrypoints/openai/completion/test_tensorizer_entrypoint.py
   commands:
     - apt-get update && apt-get install -y curl libsodium23
     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
     - pytest -v -s model_executor
-    - pytest -v -s entrypoints/openai/test_tensorizer_entrypoint.py
+    - pytest -v -s entrypoints/openai/completion/test_tensorizer_entrypoint.py

.buildkite/test_areas/plugins.yaml

@@ -36,6 +36,6 @@ steps:
   - pytest -v -s plugins_tests/test_scheduler_plugins.py
   - pip install -e ./plugins/vllm_add_dummy_model
   - pytest -v -s distributed/test_distributed_oot.py
-  - pytest -v -s entrypoints/openai/test_oot_registration.py # it needs a clean process
+  - pytest -v -s entrypoints/openai/chat_completion/test_oot_registration.py # it needs a clean process
   - pytest -v -s models/test_oot_registration.py # it needs a clean process
   - pytest -v -s plugins/lora_resolvers # unit tests for in-tree lora resolver plugins

.github/mergify.yml

@@ -381,7 +381,7 @@ pull_request_rules:
     - or:
       - files~=^vllm/model_executor/model_loader/tensorizer.py
       - files~=^vllm/model_executor/model_loader/tensorizer_loader.py
-      - files~=^tests/entrypoints/openai/test_tensorizer_entrypoint.py
+      - files~=^tests/entrypoints/openai/completion/test_tensorizer_entrypoint.py
       - files~=^tests/model_executor/model_loader/tensorizer_loader/
   actions:
     assign:

requirements/rocm-test.txt

@@ -50,7 +50,7 @@ av==16.1.0
 blobfile==3.0.0
     # Multi-Modal Models Test
 decord==0.6.0
-    # video processing, required by entrypoints/openai/test_video.py
+    # video processing, required by entrypoints/openai/chat_completion/test_video.py
 rapidfuzz==3.12.1
 
 # OpenAI compatibility and testing

tests/distributed/test_distributed_oot.py

@@ -1,7 +1,9 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
-from ..entrypoints.openai.test_oot_registration import run_and_test_dummy_opt_api_server
+from tests.entrypoints.openai.chat_completion.test_oot_registration import (
+    run_and_test_dummy_opt_api_server,
+)
 
 
 def test_distributed_oot(dummy_opt_path: str):

tests/entrypoints/llm/test_chat.py

@@ -4,12 +4,11 @@ import weakref
 
 import pytest
 
+from tests.entrypoints.openai.chat_completion.test_vision import TEST_IMAGE_ASSETS
 from vllm import LLM
 from vllm.distributed import cleanup_dist_env_and_memory
 from vllm.sampling_params import SamplingParams
 
-from ..openai.test_vision import TEST_IMAGE_ASSETS
-
 
 @pytest.fixture(scope="function")
 def text_llm():

tests/entrypoints/llm/test_mm_cache_stats.py

@@ -6,13 +6,12 @@ import logging
 import pytest
 import regex as re
 
+from tests.entrypoints.openai.chat_completion.test_vision import TEST_IMAGE_ASSETS
 from vllm import LLM
 from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
 from vllm.v1.metrics import loggers as stat_loggers
 from vllm.v1.metrics.reader import Counter, Metric
 
-from ..openai.test_vision import TEST_IMAGE_ASSETS
-
 
 def _make_messages(image_url: str) -> list[ChatCompletionMessageParam]:
     return [

tests/entrypoints/openai/chat_completion/test_audio.py

@@ -7,11 +7,10 @@ import openai
 import pytest
 import pytest_asyncio
 
+from tests.utils import RemoteOpenAIServer
 from vllm.assets.audio import AudioAsset
 from vllm.multimodal.utils import encode_audio_base64, encode_audio_url, fetch_audio
 
-from ...utils import RemoteOpenAIServer
-
 MODEL_NAME = "fixie-ai/ultravox-v0_5-llama-3_2-1b"
 TEST_AUDIO_URLS = [
     AudioAsset("winning_call").url,

tests/entrypoints/openai/chat_completion/test_audio_in_video.py

@@ -8,8 +8,8 @@ import openai
 import pytest
 import pytest_asyncio
 
-from ...conftest import VideoTestAssets
+from tests.conftest import VideoTestAssets
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 MODEL_NAME = "Qwen/Qwen2.5-Omni-3B"
 

tests/entrypoints/openai/chat_completion/test_default_mm_loras.py

@@ -8,8 +8,8 @@ import pytest
 import pytest_asyncio
 from huggingface_hub import snapshot_download
 
-from ...conftest import AudioTestAssets
+from tests.conftest import AudioTestAssets
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 # NOTE - the tests in this module are currently analogous to test_chat, but are
 # separated to avoid OOM killing due to module-scoped servers, since we

tests/entrypoints/openai/chat_completion/test_oot_registration.py

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
-from ...utils import VLLM_PATH, RemoteOpenAIServer
+from tests.utils import VLLM_PATH, RemoteOpenAIServer
 
 chatml_jinja_path = VLLM_PATH / "examples/template_chatml.jinja"
 assert chatml_jinja_path.exists()

tests/entrypoints/openai/chat_completion/test_root_path.py

@@ -8,7 +8,7 @@ from typing import Any, NamedTuple
 import openai  # use the official client for correctness check
 import pytest
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 # # any model with a chat template should work here
 MODEL_NAME = "Qwen/Qwen2-1.5B-Instruct"

tests/entrypoints/openai/chat_completion/test_video.py

@@ -7,11 +7,10 @@ import openai
 import pytest
 import pytest_asyncio
 
+from tests.utils import RemoteOpenAIServer
 from vllm.multimodal.utils import encode_video_url, fetch_video
 from vllm.platforms import current_platform
 
-from ...utils import RemoteOpenAIServer
-
 MODEL_NAME = "llava-hf/llava-onevision-qwen2-0.5b-ov-hf"
 MAXIMUM_VIDEOS = 3
 

tests/entrypoints/openai/chat_completion/test_vision.py

@@ -8,12 +8,11 @@ import pytest
 import pytest_asyncio
 from transformers import AutoProcessor
 
+from tests.utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
 from vllm.multimodal.media import MediaWithBytes
 from vllm.multimodal.utils import encode_image_url, fetch_image
 from vllm.platforms import current_platform
 
-from ...utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
-
 MODEL_NAME = "microsoft/Phi-3.5-vision-instruct"
 MAXIMUM_IMAGES = 2
 

tests/entrypoints/openai/chat_completion/test_vision_embeds.py

@@ -8,10 +8,9 @@ import pytest
 import requests
 import torch
 
+from tests.utils import RemoteOpenAIServer
 from vllm.utils.serial_utils import tensor2base64
 
-from ...utils import RemoteOpenAIServer
-
 
 @pytest.mark.parametrize(
     "model_name", ["ibm-nasa-geospatial/Prithvi-EO-2.0-300M-TL-Sen1Floods11"]

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/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/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/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")