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.
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
[onnx] support attn_mask fp16 type #110306
[onnx] support attn_mask fp16 type #110306
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/110306
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 6149727 with merge base d04b35e (): This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This looks good! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM! Thanks!
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
When users define customized
attention mask
usingdtype=torch.float16
, e.g.the onnx graph cannot be exported.
When q, k ,v have the fp16 type, we can support this
attn_mask
to befp16
type, by addingThis can export
.onnx
graph.Fixes #109336