[Bugfix] Respect VLLM_WEIGHT_OFFLOADING_DISABLE_PIN_MEMORY in prefetch offloader (#37699)
Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com> Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
@@ -8,6 +8,7 @@ from vllm.model_executor.offloader.base import (
|
||||
create_offloader,
|
||||
get_offloader,
|
||||
set_offloader,
|
||||
should_pin_memory,
|
||||
)
|
||||
from vllm.model_executor.offloader.prefetch import PrefetchOffloader
|
||||
from vllm.model_executor.offloader.uva import UVAOffloader
|
||||
@@ -20,4 +21,5 @@ __all__ = [
|
||||
"create_offloader",
|
||||
"get_offloader",
|
||||
"set_offloader",
|
||||
"should_pin_memory",
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user