-
Notifications
You must be signed in to change notification settings - Fork 142
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
Add AQT tensor parallel for float8_dynamic_quant #1078
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1078
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 3dfc799 with merge base e7b33bc (): This comment was automatically generated by Dr. CI and updates every 15 minutes. |
21711e0
to
6314d88
Compare
3b5c8f9
to
e0966cc
Compare
return return_and_correct_aliasing( | ||
func, args, kwargs, args[0]._apply_fn_to_data(lambda x: aten.slice.Tensor(x, dim, start, end, step)) | ||
) | ||
else: |
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.
what is this case btw, is this ndim==0 or some other case?
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.
Yes, it's ndim==0. I've updated the condition to check for ndim=0, instead of generic condition.
e0966cc
to
3dfc799
Compare
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.
looks good, thanks!
Added support for tensor parallel for float8_dynamic_activation_float8_weight
Added op implementations: