-
Notifications
You must be signed in to change notification settings - Fork 284
Add slicing support for fbgemm fp8 and int4 #2308
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
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2308
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit f9c6195 with merge base 35ffb26 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
||
|
||
@implements(aten.slice.Tensor) | ||
def _(func, types, args, kwargs): |
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.
Maybe a doc block here on what is supported and the semantics this code is not that easy to grok
Summary: att, this is needed in vllm Note that irregular shapes will require padding, which is not implemented right now, we can add that if it's required by the model Test Plan: python test/dtypes/test_fbgemm_fp8.py -k test_slice python test/dtypes/test_fbgemm_int4.py -k test_slice Reviewers: Subscribers: Tasks: Tags:
Summary:
att, this is needed in vllm
Note that irregular shapes will require padding, which is not implemented right now, we can add that if it's required by the model
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: