Skip to content

[ET-VK][sdpa] Expose shader override - #24390

Merged
SS-JIA merged 1 commit into
gh/SS-JIA/676/origfrom
gh/SS-JIA/677/orig
Oct 31, 2026
Merged

SS-JIA merged 1 commit into
gh/SS-JIA/676/origfrom
gh/SS-JIA/677/orig

Conversation

@pytorchbot

Copy link
Copy Markdown
Collaborator

This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #24343 by @SS-JIA
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/677/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/677/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/676/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/677/orig
Differential Revision: D128509576
@diff-train-skip-merge

Pull Request resolved: #24343

## Ulterior Motive

Benchmark SDPA shader routes without duplicating the production operator.

## Rationale

Expose `sdpa_impl_with_shader_override()` to assemble the full SDPA operator while selecting its attention-value shader. The registered operator delegates to this function with no override, preserving automatic routing and the existing QK/softmax/AV dispatch chain.

```cpp
sdpa_impl_with_shader_override(
    graph, args, graph.add_scalar(kShaderOverrideForceTile2));
```

The override is a graph scalar using the existing SDPA route constants. Validation is provided by SDPA JSON cases and route sweeps in the later `benchmark_v2` commit.

Authored with Codex (AI).
ghstack-source-id: 461636572
@exported-using-ghexport

Differential Revision: [D128509576](https://our.internmc.facebook.com/intern/diff/D128509576/)
@pytorchbot
pytorchbot requested a review from SS-JIA as a code owner October 31, 2026 16:42
@pytorch-bot

pytorch-bot Bot commented Oct 31, 2026 •

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24390

Note: Links to docs will display an error until the docs builds have been completed.

❌ 25 Pending, 6 Unclassified Failures

As of commit 7cf132e with merge base aed328d (image):

UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@meta-cla meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Oct 31, 2026
@SS-JIA
SS-JIA added this pull request to stack #24392 October 31, 2026 17:19
@SS-JIA
SS-JIA merged commit c9439f1 into main Oct 31, 2026
235 of 247 checks passed
@SS-JIA
SS-JIA deleted the gh/SS-JIA/677/orig branch October 31, 2026 17:21

This branch was previously deployed

1 inactive deployment
cadence — 7cf132ec Deployed Oct 31, 2026 by pytorchbot via hifi-op-test / hifi4 #35750
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants