[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/samplers/test_rejection_sampler.py

@@ -8,6 +8,15 @@ import torch.nn.functional as F
 from vllm.model_executor.layers.rejection_sampler import RejectionSampler
 from vllm.model_executor.utils import set_random_seed
 
+
+@pytest.fixture(scope="function", autouse=True)
+def use_v0_only(monkeypatch):
+    """
+    This file tests V0 internals, so set VLLM_USE_V1=0.
+    """
+    monkeypatch.setenv('VLLM_USE_V1', '0')
+
+
 CUDA_DEVICES = [
     f"cuda:{i}" for i in range(1 if torch.cuda.device_count() == 1 else 2)
 ]