[ci] try to add multi-node tests (#6280)

Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>

tests/async_engine/test_openapi_server_ray.py

@@ -1,35 +1,26 @@
 import openai  # use the official client for correctness check
 import pytest
-# using Ray for overall ease of process management, parallel requests,
-# and debugging.
-import ray
 
-from ..utils import VLLM_PATH, RemoteOpenAIServer
+from ..utils import RemoteOpenAIServer
 
 # any model with a chat template should work here
 MODEL_NAME = "facebook/opt-125m"
 
 
 @pytest.fixture(scope="module")
-def ray_ctx():
-    ray.init(runtime_env={"working_dir": VLLM_PATH})
-    yield
-    ray.shutdown()
-
-
-@pytest.fixture(scope="module")
-def server(ray_ctx):
-    return RemoteOpenAIServer([
-        "--model",
-        MODEL_NAME,
-        # use half precision for speed and memory savings in CI environment
-        "--dtype",
-        "float16",
-        "--max-model-len",
-        "2048",
-        "--enforce-eager",
-        "--engine-use-ray"
-    ])
+def server():
+    with RemoteOpenAIServer([
+            "--model",
+            MODEL_NAME,
+            # use half precision for speed and memory savings in CI environment
+            "--dtype",
+            "float16",
+            "--max-model-len",
+            "2048",
+            "--enforce-eager",
+            "--engine-use-ray"
+    ]) as remote_server:
+        yield remote_server
 
 
 @pytest.fixture(scope="module")