-
Notifications
You must be signed in to change notification settings - Fork 359
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
feat: Implement FP8 functionality #2763
Conversation
chore: updates to trt api chore: trt 10 fixes chore: more fixes
author Dheeraj Peri <peri.dheeraj@gmail.com> 1711393059 -0700 committer Dheeraj Peri <peri.dheeraj@gmail.com> 1711393072 -0700 chore: minor updates chore: Fix save failures chore: minor fixes chore: remove duplicate bert test case chore: remove comments chore: add load api chore: minor updates chore: minor updates chore: minor updates chore: more updates
def pre_export_lowering( | ||
ep: torch.export.ExportedProgram, sample_inputs: Sequence[torch.Tensor] | ||
) -> torch.fx.GraphModule: | ||
"""Applies the lowering passes to a graph module after torch.export/ torch.compile and their decompositions, returns the modified GraphModule""" |
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.
after
-> before
?
I'm wondering what belong to pre_lowering
and what belong to post_lowering
?
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.
remove_detach belongs to pre_lowering (which happens before decompositions and other lowering passes)
Description
This PR adds FP8 & BF16 datatype support. It also implements converter for FP8 quantized ops.
Type of change
Please delete options that are not relevant and/or add your own.
Checklist: