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 training mask strategy issue #248

Merged
merged 11 commits into from
Mar 6, 2025
Merged

fix training mask strategy issue #248

Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
377d160
fix kernel issue
jzhang38 Feb 17, 2025
722c479
Merge branch 'main' of github.com:hao-ai-lab/FastVideo
jzhang38 Feb 19, 2025
782dae2
Merge branch 'main' of github.com:hao-ai-lab/FastVideo
jzhang38 Feb 20, 2025
b267d0d
Merge branch 'main' of github.com:hao-ai-lab/FastVideo
jzhang38 Feb 21, 2025
bb27756
Added multi-GPU support for Hunyuan STA
jzhang38 Feb 21, 2025
71e64bf
Merge branch 'main' of github.com:hao-ai-lab/FastVideo into yq-dev
jzhang38 Feb 25, 2025
5814988
fix train/distill issue
jzhang38 Feb 25, 2025
1fa3f9c
syn
jzhang38 Feb 25, 2025
0bd0511
Merge branch 'main' of github.com:hao-ai-lab/FastVideo into yq-dev
jzhang38 Mar 6, 2025
85af8e8
fix training mask strategy issue
jzhang38 Mar 6, 2025
c9bc245
fix training mask strategy issue
jzhang38 Mar 6, 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
3 changes: 1 addition & 2 deletions fastvideo/models/hunyuan/modules/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -524,8 +524,7 @@ def forward(
if guidance is None:
guidance = torch.tensor([6016.0], device=hidden_states.device, dtype=torch.bfloat16)
if mask_strategy is None:
mask_strategy = [[None] * len(self.heads_num)
for _ in range(len(self.double_blocks) + len(self.single_blocks))]
mask_strategy = [[None] * self.heads_num for _ in range(len(self.double_blocks) + len(self.single_blocks))]
img = x = hidden_states
text_mask = encoder_attention_mask
t = timestep
Expand Down