[V1] Fully Transparent Implementation of CPU Offloading (#15354)

Signed-off-by: youkaichao <youkaichao@gmail.com>

tests/basic_correctness/test_cpu_offload.py

@@ -1,15 +1,8 @@
 # SPDX-License-Identifier: Apache-2.0
 
-import pytest
-
 from ..utils import compare_two_settings
 
 
-@pytest.fixture(scope="function", autouse=True)
-def use_v0_only(monkeypatch):
-    monkeypatch.setenv('VLLM_USE_V1', '0')
-
-
 def test_cpu_offload():
     compare_two_settings("meta-llama/Llama-3.2-1B-Instruct", [],
                          ["--cpu-offload-gb", "1"])