vllm/tests/basic_correctness/test_cpu_offload.py
Robert Shaw d4d93db2c5
[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>
2025-03-14 22:02:20 -07:00

16 lines
361 B
Python

# 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"])