Skip to content
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

fix device check #2136

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix device check #2136

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
4 changes: 2 additions & 2 deletions optimum/gptq/quantizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -519,7 +519,7 @@ def quantize_model(self, model: nn.Module, tokenizer: Optional[Any] = None):
blocks = recurse_getattr(model, self.block_name_to_quantize)

cur_layer_device = get_device(blocks[0])
if not is_gptqmodel_available():
if not is_gptqmodel_available() and cur_layer_device.type == "cpu":
cur_layer_device = 0

if not has_device_map:
Expand Down Expand Up @@ -591,7 +591,7 @@ def store_input_hook(_, input, *args):
block = block.to(0)
layers = get_layers(block)
block_device = get_device(block)
if not is_gptqmodel_available():
if not is_gptqmodel_available() and block_device.type == "cpu":
block_device = 0
if isinstance(self.modules_in_block_to_quantize, list) and len(self.modules_in_block_to_quantize) > 0:
if self.true_sequential:
Expand Down