Update triton and triton_shared to latest upstream#36
Merged
Conversation
Update triton_shared from aff7421 to 1850a7b (origin/main) and triton from 32b7b208d48d to 787955000d61, picking up the tptr-to-mlir::ptr refactoring and triton version bump in triton_shared. - Rebase triton_shared.patch onto new triton_shared base - Remove deleted pass `add_rewrite_tensor_pointer` from compiler.py (removed in new triton; `add_rewrite_tensor_descriptor_to_pointer` remains and is already used) - triton.patch applies cleanly without changes Tested on Strix (AIE2P): 17/18 examples pass, 1 skip (autotune-matmul). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Contributor
There was a problem hiding this comment.
Pull request overview
Updates the embedded Triton and Triton Shared upstream snapshots and adjusts the local integration patches/pipeline to stay compatible with the new upstream state.
Changes:
- Rebased
third_party/triton_shared.patchon the updatedtriton_sharedsubmodule (including updating thetriton-hash.txthunk in the patch). - Updated the NPU TTIR pipeline to remove
add_rewrite_tensor_pointer, which no longer exists upstream.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
third_party/triton_shared.patch |
Rebases the local patch content to apply cleanly on the newer triton_shared snapshot and aligns the triton-hash.txt patch hunk accordingly. |
amd_triton_npu/backend/compiler.py |
Removes a now-deleted Triton TTIR pass from the NPU compilation pipeline to keep compatibility with the newer Triton version. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
triton_sharedsubmodule fromaff7421to1850a7b(origin/main, 4 commits)tritonsubmodule from32b7b208d48dto787955000d61(148 commits)triton_shared.patchonto new base (driver.py hunk unchanged, triton-hash.txt updated)add_rewrite_tensor_pointerpass fromcompiler.py(removed in new triton)triton.patchapplies cleanly without changesUpstream changes picked up
tptr→mlir::ptrdialect refactoring in triton_shared7f77ca0d)triton-shared-opt(triton_shared, optional migration)Test plan
pip install . --no-build-isolation)--device aie2pautotune-matmul(notransform_aie2p.mlir)matvec(pre-existing, unrelated to this change)🤖 Generated with Claude Code