Skip to content

Update derived_zero initialization to use device aligned with other i… #14978

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

Update derived_zero initialization to use device aligned with other i… #14978

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
67108b6
Update derived_zero initialization to use device aligned with other i…
cccclai Oct 10, 2025
ab8d4e7
lint
cccclai Oct 13, 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 backends/qualcomm/quantizer/qconfig.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@ def _derive_bias_qparams_fn(
act_scale, weight_scale
)
derived_scale = (broadcast_act_scale * broadcast_weight_scale).to(torch.float32)
derived_zero = torch.zeros(derived_scale.size()).to(torch.int32)
derived_zero = torch.zeros(derived_scale.size(), device=weight_zp.device).to(torch.int32)
if isinstance(weight_obs_or_fq, PerBlockParamObserver):
# keep maximum scale of each channel for bias
derived_scale = (
Expand Down
Loading