Skip to content

[core] fix autoencoderkl qwenimage for xla #13480

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
sayakpaul merged 3 commits into from
Apr 16, 2026
Merged

[core] fix autoencoderkl qwenimage for xla #13480

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b0b8008
fix autoencoderkl qwenimage for xla
sayakpaul Apr 15, 2026
ff90afd
Merge branch 'main' into xla-autoencoder-qwenimage
sayakpaul Apr 16, 2026
76174db
Merge branch 'main' into xla-autoencoder-qwenimage
sayakpaul Apr 16, 2026
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
14 changes: 7 additions & 7 deletions src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,7 @@ def forward(self, x, feat_cache=None, feat_idx=[0]):
feat_cache[idx] = "Rep"
feat_idx[0] += 1
else:
cache_x = x[:, :, -CACHE_T:, :, :].clone()
cache_x = x[:, :, -min(CACHE_T, x.shape[2]) :, :, :].clone()
if cache_x.shape[2] < 2 and feat_cache[idx] is not None and feat_cache[idx] != "Rep":
# cache last frame of last two chunk
cache_x = torch.cat(
Expand Down Expand Up @@ -258,7 +258,7 @@ def forward(self, x, feat_cache=None, feat_idx=[0]):

if feat_cache is not None:
idx = feat_idx[0]
cache_x = x[:, :, -CACHE_T:, :, :].clone()
cache_x = x[:, :, -min(CACHE_T, x.shape[2]) :, :, :].clone()
if cache_x.shape[2] < 2 and feat_cache[idx] is not None:
cache_x = torch.cat([feat_cache[idx][:, :, -1, :, :].unsqueeze(2).to(cache_x.device), cache_x], dim=2)

Expand All @@ -277,7 +277,7 @@ def forward(self, x, feat_cache=None, feat_idx=[0]):

if feat_cache is not None:
idx = feat_idx[0]
cache_x = x[:, :, -CACHE_T:, :, :].clone()
cache_x = x[:, :, -min(CACHE_T, x.shape[2]) :, :, :].clone()
if cache_x.shape[2] < 2 and feat_cache[idx] is not None:
cache_x = torch.cat([feat_cache[idx][:, :, -1, :, :].unsqueeze(2).to(cache_x.device), cache_x], dim=2)

Expand Down Expand Up @@ -446,7 +446,7 @@ def __init__(
def forward(self, x, feat_cache=None, feat_idx=[0]):
if feat_cache is not None:
idx = feat_idx[0]
cache_x = x[:, :, -CACHE_T:, :, :].clone()
cache_x = x[:, :, -min(CACHE_T, x.shape[2]) :, :, :].clone()
if cache_x.shape[2] < 2 and feat_cache[idx] is not None:
# cache last frame of last two chunk
cache_x = torch.cat([feat_cache[idx][:, :, -1, :, :].unsqueeze(2).to(cache_x.device), cache_x], dim=2)
Expand All @@ -471,7 +471,7 @@ def forward(self, x, feat_cache=None, feat_idx=[0]):
x = self.nonlinearity(x)
if feat_cache is not None:
idx = feat_idx[0]
cache_x = x[:, :, -CACHE_T:, :, :].clone()
cache_x = x[:, :, -min(CACHE_T, x.shape[2]) :, :, :].clone()
if cache_x.shape[2] < 2 and feat_cache[idx] is not None:
# cache last frame of last two chunk
cache_x = torch.cat([feat_cache[idx][:, :, -1, :, :].unsqueeze(2).to(cache_x.device), cache_x], dim=2)
Expand Down Expand Up @@ -636,7 +636,7 @@ def forward(self, x, feat_cache=None, feat_idx=[0]):
## conv1
if feat_cache is not None:
idx = feat_idx[0]
cache_x = x[:, :, -CACHE_T:, :, :].clone()
cache_x = x[:, :, -min(CACHE_T, x.shape[2]) :, :, :].clone()
if cache_x.shape[2] < 2 and feat_cache[idx] is not None:
# cache last frame of last two chunk
cache_x = torch.cat([feat_cache[idx][:, :, -1, :, :].unsqueeze(2).to(cache_x.device), cache_x], dim=2)
Expand All @@ -658,7 +658,7 @@ def forward(self, x, feat_cache=None, feat_idx=[0]):
x = self.nonlinearity(x)
if feat_cache is not None:
idx = feat_idx[0]
cache_x = x[:, :, -CACHE_T:, :, :].clone()
cache_x = x[:, :, -min(CACHE_T, x.shape[2]) :, :, :].clone()
if cache_x.shape[2] < 2 and feat_cache[idx] is not None:
# cache last frame of last two chunk
cache_x = torch.cat([feat_cache[idx][:, :, -1, :, :].unsqueeze(2).to(cache_x.device), cache_x], dim=2)
Expand Down
Loading