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

Jump to bottom

MPT: Change order of operands to enable PT2 compile for inference #559

Merged
merged 2 commits into from
Aug 28, 2023
Merged

MPT: Change order of operands to enable PT2 compile for inference #559

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b64bd89
Small change to enable PT2 compile for inference
tdoublep Aug 25, 2023
e9bceed
code formatting
tdoublep Aug 26, 2023
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
5 changes: 2 additions & 3 deletions llmfoundry/models/mpt/modeling_mpt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -326,9 +326,8 @@ def forward(
'output_attentions is not implemented for MPT when using attn_impl `flash` or `triton`.'
)

if (attention_mask is not None and
attention_mask[:, 0].sum() != attention_mask.shape[0] and
self.training):
if (self.training and attention_mask is not None and
attention_mask[:, 0].sum() != attention_mask.shape[0]):
raise NotImplementedError(
'MPT does not support training with left padding.')

Expand Down
Loading