[ExecuTorch][WebGPU] Broadcast add.Tensor (mirror mul) + un-skip 6 models#21233
Open
JCNTH wants to merge 1 commit into
Open
[ExecuTorch][WebGPU] Broadcast add.Tensor (mirror mul) + un-skip 6 models#21233JCNTH wants to merge 1 commit into
JCNTH wants to merge 1 commit into
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21233
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 27 New Failures, 4 Unrelated FailuresAs of commit 4d87cce with merge base 266e0dc ( NEW FAILURES - The following jobs have failed:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Jul 22, 2026
This was referenced Jul 22, 2026
meta-cla
Bot
added
the
CLA Signed
This was referenced Jul 22, 2026
This PR needs a
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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):
add.Tensorwas elementwise-only:binary_add.wgslcomputedoutput[idx] = input1[idx] + alpha * input2[idx]over a single flat index up to the output numel, so on a broadcast it read the smaller operand out of bounds (WebGPU robustness clamps/zeros -> silently wrong, not0x30). This is the failure mode behind the models the WebGPU flow skips (resnet50,vit_b_16,swin_v2_t,convnext_small,mobilenet_v3_small,shufflenet_v2_x1_0) and thebcast_first/bcast_secondop cases.Give
add.TensorNumPy broadcasting by mirroring the shippedmul:binary_add.wgsl- copybinary_mul's kernel (rank-8TensorMetalayout from the rank-cap fix below it in the stack): keep the identical-shape elementwise fast path (common case stays bit-for-bitinput1[idx] + alpha * input2[idx]), else relinearize out idx -> per-input coords (clamp size-1 dims) and add.alphais a second pipeline-override constant (read once at build, never rewritten on resize), so no extra UBO.add/BinaryOp.cpp- portmul_impl: 3TensorMetaUBOs viafill_tensor_meta_broadcast, rank + fp32 guards, 6-entry bind group,constantCount = 2({wg_size, alpha}), 2D dispatch, andmul's resize hook verbatim (rebuild the 3 metas fromcur_dims,set_cur_dims, rewrite UBOs + dispatch);own_uniform_bufferthe 3 metas. Drops the old flatAddParamspath.flows/webgpu.py- un-skip the 6 broadcast-add models + thebcast_first/bcast_secondop cases (kept thefloat16/float64dtype skips andhardswish/lstm_batch_sizes/upsample_nearest2d).This sits above the rank-cap fix, so the shader uses the rank-8
array<vec4<u32>, 2>TensorMetalayout. Applied identically to bothxplat/andfbcode/mirrors (byte-identical).Co-authored-with: Claude Code.
Differential Revision: D113319599