Skip to content

missing offload dealloc tracking #1937

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 27, 2025
Merged

missing offload dealloc tracking #1937

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions gptqmodel/utils/offload.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
from accelerate.utils import align_module_device, has_offloaded_params
from torch import nn

from .memory import MEM_LORD
from ..looper.named_module import NamedModule
from .device import get_device
from .torch import CPU, HAS_CUDA, META
Expand Down Expand Up @@ -90,6 +91,7 @@ def _offload_disk(module: nn.Module, name: str, disk_path: str = "."):
# print(f"[skip] '{name}' is on meta; leaving as-is")
return

MEM_LORD.free(module)
m_device = get_device(module)
if m_device.type == "cuda":
torch.cuda.set_device(m_device)
Expand Down