mirror of
https://github.com/vllm-project/vllm.git
synced 2025-10-20 14:53:52 +08:00
[Core] Free CPU pinned memory on environment cleanup (#10477)
This commit is contained in:
@ -1183,6 +1183,11 @@ def cleanup_dist_env_and_memory(shutdown_ray: bool = False):
|
||||
from vllm.platforms import current_platform
|
||||
if not current_platform.is_cpu():
|
||||
torch.cuda.empty_cache()
|
||||
try:
|
||||
torch._C._host_emptyCache()
|
||||
except AttributeError:
|
||||
logger.warning(
|
||||
"torch._C._host_emptyCache() only available in Pytorch >=2.5")
|
||||
|
||||
|
||||
def in_the_same_node_as(pg: Union[ProcessGroup, StatelessProcessGroup],
|
||||
|
Reference in New Issue
Block a user