Skip to content

fix gptqmodel inference issue #813

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 4 commits into from
Sep 10, 2025
Merged

fix gptqmodel inference issue #813

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c6ab0ce
remove torch compile
wenhuach21 Sep 10, 2025
a9188f4
fix gptqmodel inference issue
wenhuach21 Sep 10, 2025
7c8e6eb
Merge branch 'main' into rm_nv_compile
wenhuach21 Sep 10, 2025
6638d22
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Sep 10, 2025
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
7 changes: 7 additions & 0 deletions auto_round/inference/backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -559,8 +559,15 @@ def dynamic_import_inference_linear(backend, config):


def get_gptqmodel_infer_linear(backend, bits=4, group_size=128, sym=False):
import torch

dtype = torch.get_default_dtype()
if dtype != torch.float32:
torch.set_default_dtype(torch.float32)
import gptqmodel # pylint: disable=E0401

torch.set_default_dtype(dtype)

if "marlin" in backend:
return auto_round_extension.cuda.gptqmodel_marlin.get_marlin_layer()
# return gptqmodel.nn_modules.qlinear.marlin.MarlinQuantLinear
Expand Down
Loading