Update triton xpu commit pin #137886
Update triton xpu commit pin #137886
Conversation
guangyey
requested review from
a team,
EikanWang and
gujinghui
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/137886
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 bc428ce with merge base 9b89fa4 ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
UNSTABLE - The following job failed but was likely due to flakiness present on trunk and has been marked as unstable:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
guangyey
added
ciflow/xpu
|
These failures are related with intel/intel-xpu-backend-for-triton#2488. |
guangyey
changed the title
|
@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here |
|
Successfully rebased |
|
@pytorchbot rebase |
|
@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here |
|
Successfully rebased |
|
The only one UT failure appeared in doctests, there is an issue to track it #141705 |
|
@pytorchbot merge -i |
Merge startedYour change will be merged while ignoring the following 2 checks: inductor / cuda12.1-py3.10-gcc9-sm86 / test (inductor_timm, 1, 2, linux.g5.4xlarge.nvidia.gpu), xpu / linux-jammy-xpu-2025_0-py3.9 / test (default, 1, 4, linux.idc.xpu) Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
# Motivation Due to the code change of pytorch#135567, triton-xpu needs to fetch `tensor.data_ptr()` via `uint64` instead of `int64`, refer to intel/intel-xpu-backend-for-triton#2192 # Additional Context triton commit comes from release branch: https://github.com/intel/intel-xpu-backend-for-triton/tree/release/3.2.0 Pull Request resolved: pytorch#137886 Approved by: https://github.com/EikanWang, https://github.com/atalman ghstack dependencies: pytorch#135567
Triton xpu build was stopped by pytorch#139206 temporally to wait triton xpu upgrade PR pytorch#137886 landed. Works for pytorch#139722 and pytorch#114850 Pull Request resolved: pytorch#141775 Approved by: https://github.com/atalman
7 participants
Stack from ghstack (oldest at bottom):
Motivation
Due to the code change of #135567, triton-xpu needs to fetch
tensor.data_ptr()viauint64instead ofint64, refer to intel/intel-xpu-backend-for-triton#2192Additional Context
triton commit comes from release branch: https://github.com/intel/intel-xpu-backend-for-triton/tree/release/3.2.0