[1/N] Elastic EP Milestone 2 (#34861)

Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>

tests/conftest.py

@@ -176,16 +176,20 @@ def init_test_http_connection():
 
 @pytest.fixture
 def dist_init():
+    from tests.utils import ensure_current_vllm_config
+
     temp_file = tempfile.mkstemp()[1]
-    init_distributed_environment(
-        world_size=1,
-        rank=0,
-        distributed_init_method=f"file://{temp_file}",
-        local_rank=0,
-        backend="nccl",
-    )
-    initialize_model_parallel(1, 1)
-    yield
+
+    with ensure_current_vllm_config():
+        init_distributed_environment(
+            world_size=1,
+            rank=0,
+            distributed_init_method=f"file://{temp_file}",
+            local_rank=0,
+            backend="nccl",
+        )
+        initialize_model_parallel(1, 1)
+        yield
     cleanup_dist_env_and_memory()