[ExecuTorch][WebGPU] Test apply_rotary_emb_interleaved#21186
Open
JCNTH wants to merge 2 commits into
Open
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21186
Note: Links to docs will display an error until the docs builds have been completed. ❌ 5 New Failures, 32 Pending, 70 Unrelated FailuresAs of commit c473973 with merge base 4a26c64 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
This was referenced Jul 22, 2026
This was referenced Jul 22, 2026
psiddh
approved these changes
Jul 23, 2026
psiddh
left a comment
psiddh
left a comment
Contributor
There was a problem hiding this comment.
Approving full WebGPU stack
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack from ghstack (oldest at bottom):
Problem: The new
apply_rotary_emb_interleavedWebGPU op needs golden coverage against a trusted reference and an export-delegation smoke test, matching the sibling rope ops.Solution: Add an op-test suite that goldens the WebGPU kernel against the CPU eager
et_vk.apply_rotary_emb_interleavedop (its own dtype-agnostic reference), plus an export test asserting the op is absorbed into the delegate rather than left as a CPU fallback.Implementation:
cases.pyregisters_rope_interleaved_suiteover bnc/batch/c4/c16 shapes at atol=rtol=1e-3 with the default fp64 dual-oracle (fp32-eager vs fp64-golden gate).test_rope_interleaved.pycalls the custom op directly (EdgeTAM has no aten lowering / fusion pattern for it) and verifies bothVulkanBackenddelegation and that nointerleavednode is left top-level.@exported-using-ghexport
Differential Revision: D112257606
Differential Revision: D112257606