-
Notifications
You must be signed in to change notification settings - Fork 74
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
Opt LN_sharded and SMX_sharded #4147
Conversation
yugaoTT
commented
Dec 2, 2023
- for SMX, remove wait_front to avoid unpacker packer sync
- for LN, finished compute for one block in one run before switching to another compute section.
@@ -171,7 +171,7 @@ def test_perf_virtual_machine( | |||
@pytest.mark.models_performance_bare_metal | |||
@pytest.mark.parametrize( | |||
"expected_inference_time, expected_compile_time, inference_iterations", | |||
([0.0375, 10, 10],), | |||
([0.0364, 10, 10],), |
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.
To tighten inference time tolerance, please run the model 3 times on CI and average the inference time and consider 15% tolerance.
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.
Thanks for the advice, I have ran it for 3 times and passed with fps ~338
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.
Hey @farbabi, if there is no other things needs change/test, could I get an approval? thanks
@boris-drazic just a reminder that the PR needs your approval :). I'd appreciate it if you can take a look at the changes |
65447a0
to
3eb0ec7
Compare
3eb0ec7
to
cbe97c2
Compare