[Misc] Improve organization of utility and test code

format.sh

@@ -113,8 +113,11 @@ mypy vllm/logging --config-file pyproject.toml
 mypy vllm/model_executor --config-file pyproject.toml
 
 
+# If git diff returns a file that is in the skip list, the file may be checked anyway:
+# https://github.com/codespell-project/codespell/issues/1915
+# Avoiding the "./" prefix and using "/**" globs for directories appears to solve the problem
 CODESPELL_EXCLUDES=(
-    '--skip' '*docs/source/_build/**,./tests/lora/data'
+    '--skip' 'tests/prompts/**,./benchmarks/sonnet.txt,tests/lora/data/**,build/**'
 )
 
 # check spelling of specified files

tests/async_engine/test_openapi_server_ray.py

@@ -4,16 +4,22 @@
 # and debugging.
 import ray
 
-from ..utils import ServerRunner
+from ..utils import VLLM_PATH, RemoteOpenAIServer
 
 # any model with a chat template should work here
 MODEL_NAME = "facebook/opt-125m"
 
 
 @pytest.fixture(scope="module")
-def server():
-    ray.init()
-    server_runner = ServerRunner.remote([
+def ray_ctx():
+    ray.init(runtime_env={"working_dir": VLLM_PATH})
+    yield
+    ray.shutdown()
+
+
+@pytest.fixture(scope="module")
+def server(ray_ctx):
+    yield RemoteOpenAIServer([
         "--model",
         MODEL_NAME,
         # use half precision for speed and memory savings in CI environment
@@ -24,22 +30,15 @@ def server():
         "--enforce-eager",
         "--engine-use-ray"
     ])
-    ray.get(server_runner.ready.remote())
-    yield server_runner
-    ray.shutdown()
 
 
 @pytest.fixture(scope="module")
-def client():
-    client = openai.AsyncOpenAI(
-        base_url="http://localhost:8000/v1",
-        api_key="token-abc123",
-    )
-    yield client
+def client(server):
+    yield server.get_async_client()
 
 
 @pytest.mark.asyncio
-async def test_check_models(server, client: openai.AsyncOpenAI):
+async def test_check_models(client: openai.AsyncOpenAI):
     models = await client.models.list()
     models = models.data
     served_model = models[0]
@@ -48,7 +47,7 @@ async def test_check_models(server, client: openai.AsyncOpenAI):
 
 
 @pytest.mark.asyncio
-async def test_single_completion(server, client: openai.AsyncOpenAI):
+async def test_single_completion(client: openai.AsyncOpenAI):
     completion = await client.completions.create(model=MODEL_NAME,
                                                  prompt="Hello, my name is",
                                                  max_tokens=5,
@@ -74,7 +73,7 @@ async def test_single_completion(server, client: openai.AsyncOpenAI):
 
 
 @pytest.mark.asyncio
-async def test_single_chat_session(server, client: openai.AsyncOpenAI):
+async def test_single_chat_session(client: openai.AsyncOpenAI):
     messages = [{
         "role": "system",
         "content": "you are a helpful assistant"

tests/core/test_block_manager.py

@@ -136,7 +136,6 @@ def test_append_slot_cow():
                       inputs={
                           "prompt": "one two three",
                           "prompt_token_ids": [1, 2, 3],
-                          "multi_modal_data": None
                       },
                       block_size=block_size)
 
@@ -311,7 +310,6 @@ def test_sliding_window_multi_seq():
                       inputs={
                           "prompt": "one two three",
                           "prompt_token_ids": [0, 1, 2],
-                          "multi_modal_data": None
                       },
                       block_size=block_size)
     seq_group = SequenceGroup(request_id="1",

tests/core/utils.py

@@ -25,7 +25,6 @@ def create_dummy_prompt(
                       inputs={
                           "prompt": prompt_str,
                           "prompt_token_ids": prompt_tokens,
-                          "multi_modal_data": None,
                       },
                       block_size=block_size)
     seq_group = SequenceGroup(request_id=request_id,
@@ -57,11 +56,7 @@ def create_seq_group(
     for seq_id_offset, output_len in enumerate(seq_output_lens):
         seq = Sequence(
             seq_id=seq_id_start + seq_id_offset,
-            inputs={
-                "prompt": "",
-                "prompt_token_ids": prompt_token_ids,
-                "multi_modal_data": None,
-            },
+            inputs={"prompt_token_ids": prompt_token_ids},
             block_size=16,
         )
 

tests/engine/output_processor/test_stop_checker.py

@@ -15,11 +15,7 @@ def sequence_with_eos(text: str, eos_token: str,
     """
     seq = Sequence(
         seq_id=0,
-        inputs={
-            "prompt": "",
-            "prompt_token_ids": [],
-            "multi_modal_data": None,
-        },
+        inputs={"prompt_token_ids": []},
         block_size=16,
         eos_token_id=eos_token_id,
     )