-
Notifications
You must be signed in to change notification settings - Fork 362
feat: Support flashinfer.rmsnorm #3424
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
py/torch_tensorrt/dynamo/conversion/plugins/_generate_plugin.py
Outdated
Show resolved
Hide resolved
py/torch_tensorrt/dynamo/conversion/plugins/_generate_plugin.py
Outdated
Show resolved
Hide resolved
@bowang007 Can you move the auto plugin gen tests to a runner other than the one used for converter tests? |
py/torch_tensorrt/dynamo/conversion/plugins/_generate_plugin.py
Outdated
Show resolved
Hide resolved
3cc6ecb
to
aed7cb1
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.
It looks like flashiner-python
installation is problematic on CI. After resolving this issue, can you also check if this works for python 3.13 because we are going to support 3.13 as of 2.7 release while some packages may not be available for 3.13.
@zewenli98 I think this is expected since in the official doc it says it supports until python 3.12 here: https://docs.flashinfer.ai/installation.html |
aed7cb1
to
85d7b25
Compare
I updated the requirements.txt to get the python3.13 restriction @zewenli98 |
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
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.
I saw some CI errors, not sure if that's related. I restarted the failed jobs. If they pass then LGTM
…add flashinfer.rmsnorm support test case
85d7b25
to
00ddd55
Compare
This PR resolves some issues and support flashinfer.rmsnorm
Checklist: