Skip to content

Conversation

dhonnappa-amd
Copy link

Cherry-pick of #2440

#2440)

This PR has fixes for P1 Jira
https://ontrack-internal.amd.com/browse/SWDEV-542659.
In this Jira, there are 3 test files with failing tests.
1) distributed.test_distributed_spawn
2) test_binary_ufuncs
3) test_nn 

The test files **distributed.test_distributed_spawn** &
**test_binary_ufuncs** are passing with latest mainline build-

**registry-sc-harbor.amd.com/framework/compute-rocm-dkms-no-npi-hipclang:16426_ubuntu22.04_py3.10_pytorch_lw_release-2.7_fe3d37a9**.

The test file **test_nn** has 2 failing tests-
**test_batchnorm_3D_train_NCHW_vs_native_mixed_float16** &
**test_RNN_dropout_state**.
The **test_batchnorm_3D_train_NCHW_vs_native_mixed_float16** test is
skipped from PR #2370.
The **test_RNN_dropout_state** is fixed by cherry picking upstream
commit 1aa971a.

Tested on MI200 with docker image-

**registry-sc-harbor.amd.com/framework/compute-rocm-dkms-no-npi-hipclang:16426_ubuntu22.04_py3.10_pytorch_lw_release-2.7_fe3d37a9**.

---------

Co-authored-by: Iurii Paikov <iurii.paikov@amd.com>
Co-authored-by: Jeff Daily <jeff.daily@amd.com>
Co-authored-by: Nikita Shulga <2453524+malfet@users.noreply.github.com>
@rocm-repo-management-api
Copy link

rocm-repo-management-api bot commented Aug 13, 2025

Jenkins build for 2a5595e1598a606ba639773cddac0787d0c24228 commit finished as FAILURE
Links: Blue Ocean view / Build artifacts

@akashveramd akashveramd self-assigned this Aug 14, 2025
@akashveramd akashveramd marked this pull request as ready for review August 14, 2025 20:03
@jeffdaily jeffdaily changed the title [AUTOGENERATED] [release/2.8] [release/2.7] Fix test_rnn_check_device tests for P1 Jira SWDEV-542659 [release/2.8] Fix test_rnn_check_device tests for P1 Jira SWDEV-542659 Aug 15, 2025
Copy link
Collaborator

@jeffdaily jeffdaily left a comment

Choose a reason for hiding this comment

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

This doesn't look right. Formatting is all that changed, and the TORCH_CUDA_CPP_API macro is removed but it should remain.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants