[V1] V1 Enablement Oracle (#13726)

Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>

tests/async_engine/test_api_server.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: Apache-2.0
 
+import os
 import subprocess
 import sys
 import time
@@ -44,7 +45,10 @@ def api_server(tokenizer_pool_size: int, distributed_executor_backend: str):
         distributed_executor_backend,
     ]
 
-    uvicorn_process = subprocess.Popen(commands)
+    # API Server Test Requires V0.
+    my_env = os.environ.copy()
+    my_env["VLLM_USE_V1"] = "0"
+    uvicorn_process = subprocess.Popen(commands, env=my_env)
     yield
     uvicorn_process.terminate()