Skip to content

[ExecuTorch][WebGPU] Add per-pass dispatch ordering + scratch buffer tests#20194

Merged
JulianCloudNTH merged 1 commit into
gh/JulianCloudNTH/14/origfrom
gh/JulianCloudNTH/15/orig
Jun 10, 2026
Merged

[ExecuTorch][WebGPU] Add per-pass dispatch ordering + scratch buffer tests#20194
JulianCloudNTH merged 1 commit into
gh/JulianCloudNTH/14/origfrom
gh/JulianCloudNTH/15/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: #20080 by @JulianCloudNTH
^ 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/JulianCloudNTH/15/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/15/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/14/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/JulianCloudNTH/15/orig

@diff-train-skip-merge

…tests

Pull Request resolved: #20080

Native unit tests for two runtime enablers: per-pass compute-dispatch ordering (D107543258) and graph-owned scratch buffers (D107543259). `test/native/test_dispatch_order.cpp` exercises multi-dispatch read-after-write ordering through a single `execute()` using dependency chains -- a single-input `add` self-chain and a heterogeneous `rms_norm` -> `add` chain, both lowered via `VulkanPartitioner` -- comparing GPU output to a torch-computed golden per element. `test/native/test_scratch_buffer.cpp` is a white-box test of `WebGPUGraph::create_scratch_buffer` (no black-box consumer exists below the SDPA op): allocation + zero-size guard, copy round-trip, a compute Storage round-trip (its actual use), and a create/destroy lifecycle stress. Authored with assistance from Claude.
ghstack-source-id: 391979580
@exported-using-ghexport

Differential Revision: [D107576199](https://our.internmc.facebook.com/intern/diff/D107576199/)
@pytorch-bot

pytorch-bot Bot commented Jun 10, 2026

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20194

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

❌ 2 New Failures, 11 Pending, 1 Unrelated Failure

As of commit df60899 with merge base af92b60 (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following job failed but was likely due to flakiness present on trunk:

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 Jun 10, 2026
@JulianCloudNTH JulianCloudNTH merged commit 938c62d into gh/JulianCloudNTH/14/orig Jun 10, 2026
174 of 178 checks passed
@JulianCloudNTH JulianCloudNTH deleted the gh/JulianCloudNTH/15/orig branch June 10, 2026 19:53
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