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 onnx non-exportable inplace aten op #34376

Merged
merged 4 commits into from
Oct 25, 2024
Merged

Fix onnx non-exportable inplace aten op #34376

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
12355ee
fix onnx non-expotable inplace op
IlyasMoutawwakil Oct 24, 2024
5f8fe2e
mistral, qwen2, qwen2_vl, starcoder2
IlyasMoutawwakil Oct 24, 2024
f180bf0
fixup copies
IlyasMoutawwakil Oct 24, 2024
31a29a7
Merge branch 'main' into non-exportable-inplace-op
IlyasMoutawwakil Oct 25, 2024
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 src/transformers/models/mimi/modeling_mimi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1156,7 +1156,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/mistral/modeling_mistral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -961,7 +961,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/mixtral/modeling_mixtral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1174,7 +1174,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
4 changes: 2 additions & 2 deletions src/transformers/models/moshi/modeling_moshi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1385,7 +1385,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down Expand Up @@ -1689,7 +1689,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/phi3/modeling_phi3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1136,7 +1136,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/phimoe/modeling_phimoe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1305,7 +1305,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/qwen2/modeling_qwen2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1059,7 +1059,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/qwen2_moe/modeling_qwen2_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1239,7 +1239,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/qwen2_vl/modeling_qwen2_vl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1321,7 +1321,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/starcoder2/modeling_starcoder2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1033,7 +1033,7 @@ def _prepare_4d_causal_attention_mask_with_cache_position(
sliding_attend_mask = torch.arange(target_length, device=device) <= (
cache_position.reshape(-1, 1) - config.sliding_window
)
diagonal_attend_mask |= sliding_attend_mask
diagonal_attend_mask.bitwise_or_(sliding_attend_mask)
causal_mask *= diagonal_attend_mask
causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1)
if attention_mask is not None:
Expand Down
Loading