Update to transformers v5 (#30566)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: khluu <khluu000@gmail.com> Signed-off-by: Kevin H. Luu <khluu000@gmail.com> Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com> Co-authored-by: khluu <khluu000@gmail.com> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com> Co-authored-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
co-authored by
khluu
Cyrus Leung
jiang1.li
parent
6dc9491406
commit
03f8d3a548
@@ -3,6 +3,7 @@
|
||||
|
||||
import tempfile
|
||||
from collections import OrderedDict
|
||||
from importlib import reload
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
import pytest
|
||||
@@ -47,6 +48,11 @@ def cleanup_fixture(should_do_global_cleanup_after_test: bool):
|
||||
def maybe_enable_lora_dual_stream(monkeypatch: pytest.MonkeyPatch):
|
||||
if current_platform.is_cuda():
|
||||
monkeypatch.setenv("VLLM_LORA_ENABLE_DUAL_STREAM", "1")
|
||||
import vllm.lora.layers.base_linear
|
||||
|
||||
if not hasattr(vllm.lora.layers.base_linear, "lora_linear_async"):
|
||||
# Reload the module to ensure the environment variable takes effect.
|
||||
reload(vllm.lora.layers.base_linear)
|
||||
yield
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user