Skip to content

Conversation

@jeffbolznv
Copy link
Collaborator

The OOB calculation could be wrong if the last iteration was during one of the unrolled loops. Adjust the unrolling counts to avoid this. Add a couple new backend tests that hit this failure on NVIDIA GPUs.

This fixes a failure that showed up in some new tests added in #12505.

The OOB calculation could be wrong if the last iteration was during one of
the unrolled loops. Adjust the unrolling counts to avoid this. Add a couple
new backend tests that hit this failure on NVIDIA GPUs.
@jeffbolznv jeffbolznv requested a review from 0cc4m March 23, 2025 14:56
@github-actions github-actions bot added testing Everything test related Vulkan Issues specific to the Vulkan backend ggml changes relating to the ggml tensor library for machine learning labels Mar 23, 2025
@0cc4m
Copy link
Collaborator

0cc4m commented Mar 23, 2025

@stduhpf Can you check this fixes it on Windows? I'll test it on Linux.

@stduhpf
Copy link
Contributor

stduhpf commented Mar 23, 2025

All tests pass on windows!

@netrunnereve
Copy link
Collaborator

Everything's passing on my end as well!

Copy link
Collaborator

@0cc4m 0cc4m left a comment

Choose a reason for hiding this comment

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

I also confirmed this fixed it. Thank you.

@0cc4m 0cc4m merged commit 9b169a4 into ggml-org:master Mar 24, 2025
48 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning testing Everything test related Vulkan Issues specific to the Vulkan backend

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants