Skip to content

[tests] fix audioldm2 for transformers main. #11522

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 1 commit into from
May 8, 2025
Merged

[tests] fix audioldm2 for transformers main. #11522

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 13 additions & 1 deletion src/diffusers/pipelines/audioldm2/pipeline_audioldm2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@
logging,
replace_example_docstring,
)
from ...utils.import_utils import is_transformers_version
from ...utils.torch_utils import randn_tensor
from ..pipeline_utils import AudioPipelineOutput, DiffusionPipeline
from .modeling_audioldm2 import AudioLDM2ProjectionModel, AudioLDM2UNet2DConditionModel
Expand Down Expand Up @@ -312,8 +313,19 @@ def generate_language_model(
`inputs_embeds (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
The sequence of generated hidden-states.
"""
cache_position_kwargs = {}
if is_transformers_version("<", "4.52.0.dev0"):
cache_position_kwargs["input_ids"] = inputs_embeds
cache_position_kwargs["model_kwargs"] = model_kwargs
else:
cache_position_kwargs["seq_length"] = inputs_embeds.shape[0]
cache_position_kwargs["device"] = (
self.language_model.device if getattr(self, "language_model", None) is not None else self.device
)
cache_position_kwargs["model_kwargs"] = model_kwargs
max_new_tokens = max_new_tokens if max_new_tokens is not None else self.language_model.config.max_new_tokens
model_kwargs = self.language_model._get_initial_cache_position(inputs_embeds, model_kwargs)
model_kwargs = self.language_model._get_initial_cache_position(**cache_position_kwargs)

for _ in range(max_new_tokens):
# prepare model inputs
model_inputs = prepare_inputs_for_generation(inputs_embeds, **model_kwargs)
Expand Down