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.

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

Assert correct device when dequantizing (like we do for quantizing) #90

Merged
merged 2 commits into from
Jun 19, 2024
Merged
Changes from all commits
Commits
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
8 changes: 8 additions & 0 deletions src/compressed_tensors/quantization/lifecycle/forward.py
Original file line number Diff line number Diff line change
Expand Up @@ -93,6 +93,14 @@ def dequantize(
:param args: quantization args used to quantize x_q
:return: dequantized float tensor
"""
# ensure all tensors are on the same device
# assumes that the target device is the input
# tensor's device
if x_q.device != scale.device:
scale = scale.to(x_q.device)
if x_q.device != zero_point.device:
zero_point = zero_point.to(x_q.device)

if args is None:
if scale.ndim == 0 or scale.ndim == 1:
args = QuantizationArgs(strategy=QuantizationStrategy.TENSOR)
Expand Down
Loading