Skip to content

Fix bug with Intel GPUs. #47

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
Tps-F merged 3 commits into from
Jul 13, 2025
Merged

Fix bug with Intel GPUs. #47

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c837d50
Fix bug with Intel GPUs.
alcoftTAO Nov 10, 2024
f024707
Updated .gitignore
alcoftTAO Jul 13, 2025
5af9dc8
Merge branch 'RVC-Project:develop' into intel_support
alcoftTAO Jul 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
4 changes: 4 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,3 +6,7 @@ __pycache__/
*$py.class

.DS_Store
test.py
.gitignore
input.wav
output.wav
8 changes: 7 additions & 1 deletion rvc/lib/infer_pack/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -392,6 +392,12 @@ def forward(self, f0: torch.Tensor, upp: int):
output uv: tensor(batchsize=1, length, 1)
"""
with torch.no_grad():
device = next(self.parameters(), None)
if device is not None:
device = device.device
else:
device = f0.device
align_corners = device.type != "xpu"
f0 = f0[:, None].transpose(1, 2)
f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device)
# fundamental component
Expand All @@ -412,7 +418,7 @@ def forward(self, f0: torch.Tensor, upp: int):
tmp_over_one.transpose(2, 1),
scale_factor=float(upp),
mode="linear",
align_corners=True,
align_corners=align_corners,
).transpose(2, 1)
rad_values = F.interpolate(
rad_values.transpose(2, 1), scale_factor=float(upp), mode="nearest"
Expand Down