Skip to content

Fix rtn tuning_device issue #893

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 2 commits into from
Oct 14, 2025
Merged

Fix rtn tuning_device issue #893

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
83de0d9
fix rtn tuning_device
Kaihui-intel Oct 14, 2025
0719221
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Oct 14, 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
2 changes: 1 addition & 1 deletion auto_round/compressors/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1422,7 +1422,7 @@ def _quantize_layer_via_rtn(self, name: str) -> None:
m.zp = None
else:
try:
m = m.to(self.device)
m = m.to(m.tuning_device if hasattr(m, "tuning_device") else self.device)
m = WrapperLinear(
m,
enable_minmax_tuning=False,
Expand Down
13 changes: 13 additions & 0 deletions test/test_cuda/test_multiple_card.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,6 +242,19 @@ def test_device_map_dict(self):
)
autoround.quantize()

# test rtn
autoround = AutoRound(
model_name,
tokenizer,
bits=bits,
group_size=group_size,
sym=sym,
iters=0,
seqlen=2,
device_map=device_map,
)
autoround.quantize()

@multi_card
@require_greater_than_050
def test_device_map_for_triton(self):
Expand Down