Skip to content
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.

Sign up for GitHub

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

Jump to bottom

patch potential segfault #3262

Open
wants to merge 12 commits into
base: main
Choose a base branch
from
Open

patch potential segfault #3262

wants to merge 12 commits into from
+160 −5

Conversation

jjsjann123
Copy link
Collaborator

Not sure how this could happen.

@jjsjann123
Copy link
Collaborator Author

!build

jacobhinkle
jacobhinkle approved these changes Oct 24, 2024
View reviewed changes
Copy link
Collaborator

@jacobhinkle jacobhinkle left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

naoyam
naoyam requested changes Oct 24, 2024
View reviewed changes
Copy link
Collaborator

@naoyam naoyam left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you please add a repro?

@jjsjann123
Copy link
Collaborator Author

!build

@jjsjann123
Copy link
Collaborator Author

!build

@jjsjann123
Copy link
Collaborator Author

jjsjann123 commented Oct 25, 2024 •
edited
Loading

Saw this in the CI that could be relevant.

00:21:30 [ RUN      ] ResizeTest.CatMemoryPromotionReducedFloating
00:21:30 To reproduce: NVFUSER_TEST_RANDOM_SEED=1729857248 NVFUSER_TEST_ATEN_RANDOM_SEED=0 nvfuser_tests --gtest_filter='ResizeTest.CatMemoryPromotionReducedFloating'
00:21:30 unknown file: Failure
00:21:30 C++ exception with description " INTERNAL ASSERT FAILED at "/opt/pytorch/nvfuser/tests/cpp/validator.cpp":111, please report a bug with repro script to NVFuser at https://github.com/NVIDIA/Fuser/issues. 
00:21:30 
00:21:30 Validation error in output 0 on line 3541 in file /opt/pytorch/nvfuser/tests/cpp/test_resize.cpp.
00:21:30   Detected max abs error of: 6.05469
00:21:30     absolute tolerance was set to 0.00390625
00:21:30     and relative tolerance set to 0.0078125

Oops, indeed caused by the changes in this PR. Working on it now.

@jjsjann123
Copy link
Collaborator Author

!build

@jjsjann123
Copy link
Collaborator Author

!build

@jjsjann123
Copy link
Collaborator Author

tagging @naoyam for the added test.

naoyam
naoyam reviewed Oct 25, 2024
View reviewed changes
csrc/ir/utils.cpp Outdated Show resolved Hide resolved
@jjsjann123
Copy link
Collaborator Author

!build

@jjsjann123
Copy link
Collaborator Author

!build

@jjsjann123
Copy link
Collaborator Author

CI looks promising.

naoyam
naoyam approved these changes Oct 26, 2024
View reviewed changes
Copy link
Collaborator

@naoyam naoyam left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jacobhinkle jacobhinkle jacobhinkle approved these changes

@naoyam naoyam naoyam approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@jjsjann123 @naoyam @jacobhinkle