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 bug that caused ViT models to raise errors. #1374

Merged
merged 1 commit into from
Mar 5, 2025
Merged

Fix bug that caused ViT models to raise errors. #1374

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion model_compression_toolkit/core/common/graph/memory_graph/compute_graph_max_cut.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@

def compute_graph_max_cut(memory_graph: MemoryGraph,
n_iter: int = 50,
astar_n_iter: int = 500,
astar_n_iter: int = 1000,
eps: float = 1e-2) -> Tuple[List[BaseNode], float, List[Cut]]:
"""
A wrapper function to compute max cut and schedule for a given model.
Expand Down
2 changes: 1 addition & 1 deletion ...on_toolkit/core/pytorch/graph_substitutions/substitutions/scaled_dot_product_attention.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@ def _get_matmul_node(self, attention_node_name: str, q_node: BaseNode, transpose
matmul_name = f'{attention_node_name}_matmul1'
return FunctionalNode(name=matmul_name,
framework_attr={},
input_shape=(tuple(q_node.output_shape[0]), tuple(transposed_k_node.output_shape)),
input_shape=(tuple(q_node.output_shape[0]), tuple(transposed_k_node.output_shape[0])),
output_shape=tuple(matmul1_output_shape),
weights={},
layer_class=torch.matmul,
Expand Down