d4d93db2c5
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>
16 lines
361 B
Python
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"])
|