[xpu][fix] Fix conv1d precision error#162944
[xpu][fix] Fix conv1d precision error#162944yucai-intel wants to merge 17 commits intopytorch:mainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/162944
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (2 Unrelated Failures)As of commit 4bb85cd with merge base 3e4faca ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@pytorchbot rebase |
|
@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here |
|
Successfully rebased |
324991f to
686830b
Compare
|
@EikanWang or @gujinghui can you please review this PR? |
EikanWang
left a comment
There was a problem hiding this comment.
LGTM. Pls. fix the CI failures.
|
@pytorchbot rebase |
|
@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here |
|
Successfully rebased |
74ea57a to
ec9914c
Compare
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Merge failedReason: 1 jobs have failed, first few of them are: trunk / linux-jammy-rocm-py3.10 / test (default, 1, 2, linux.rocm.gpu.gfx942.1) Details for Dev Infra teamRaised by workflow job |
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Currently, conv1d converts the 3D view to 4D before calling onednn::convolution(). However, this function converts the 4D tensor to a channel-last memory format for computation, resulting in incorrect return results (the correct result should be channel-first). This PR fixes this issue, ensuring that the output return value format is consistent with the expected format. Pull Request resolved: pytorch#162944 Approved by: https://github.com/EikanWang
Currently, conv1d converts the 3D view to 4D before calling onednn::convolution().
However, this function converts the 4D tensor to a channel-last memory format for computation, resulting in incorrect return results (the correct result should be channel-first).
This PR fixes this issue, ensuring that the output return value format is consistent with the expected format.
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10 @jerryzh168 @aditew01