[ExecuTorch][WebGPU] Cover Conv1d routes and dynamic manifests - #21666
Merged
Conversation
[ghstack-poisoned]
Pull Request resolved: #21601 **Cover Conv1d routing, resize, and dynamic manifest replay** Static numeric coverage pins the general groups=1 Conv1d kernel while preserving pointwise and depthwise routing. The manifest harness now separates upper-bound export inputs from live runtime inputs so dynamic execution proves a distinct shape through one loaded graph. Key changes: - Dispatch assertions distinguish general, pointwise, and depthwise Conv1d routes. - Numeric cases cover padding, dilation, batching, optional bias, and dynamic resize. - `Case.export_inputs` and `Case.dynamic_shapes` carry export-time samples and constraints while `Case.inputs` remains the live runtime input. - Generator coverage proves export length 10 and runtime length 7. This is coverage-only; runtime kernels are unchanged. Co-authored-with: Claude Code. ghstack-source-id: 411059163 @exported-using-ghexport Differential Revision: [D114936144](https://our.internmc.facebook.com/intern/diff/D114936144/)
pytorchbot
requested review from
SS-JIA,
kirklandsign and
larryliu0820
as code owners
August 7, 2026 17:23
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21666
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
…nstruction Pull Request resolved: #21602 **Run production FastVLM shapes with exception-safe WebGPU graph construction** Production FastVLM tensors exceeded WebGPU one-dimensional dispatch limits, while several parameter buffers were not graph-owned before fallible pipeline construction. The runtime now folds flat dispatches across x/y, owns parameters immediately, rejects ambiguous `BOOL`/byte-integer casts, and compiles timestamp validation only in profiling builds. Key changes: - `GELU` and `expand_copy` use overflow-safe folded dispatch and live resize updates. - `Compare`, `expand_copy`, and `to_copy` create graph-owned parameter buffers before pipeline construction, mirroring Vulkan `ComputeGraph` ownership. - `to_copy` rejects `BOOL`-to/from-`INT8` or `UINT8` before same-width flat-copy routing. - Production builds exclude timestamp-query validation and symbols. - Boundary, failure, and real FastVLM encoder coverage exercise the final combined behavior. Kernel math and below-limit one-dimensional dispatch behavior are unchanged. Co-authored-with: Claude Code. ghstack-source-id: 411059172 @exported-using-ghexport Differential Revision: [D114936147](https://our.internmc.facebook.com/intern/diff/D114936147/)
Contributor
|
@copilot resolve the merge conflicts in this pull request |
…/208/orig # Conflicts: # backends/webgpu/runtime/WebGPUGraph.cpp # backends/webgpu/test/native/test_compute_dispatch.cpp # backends/webgpu/test/native/test_dynamic_shape.cpp # backends/webgpu/test/ops/dynamic_shape/test_dynamic_shape_export.py Co-authored-by: JCNTH <107437036+JCNTH@users.noreply.github.com>
Contributor
Merge conflicts resolved. The four conflicted files have been merged with |
meta-cla
Bot
added
the
CLA Signed
JCNTH
pushed a commit
that referenced
this pull request
Aug 7, 2026
Copilot stopped work on behalf of
JCNTH due to an error
August 7, 2026 17:32
JCNTH
pushed a commit
that referenced
this pull request
Aug 7, 2026
JCNTH
pushed a commit
that referenced
this pull request
Aug 7, 2026
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #21601 by @JCNTH
^ 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/JCNTH/208/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/JCNTH/208/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/JCNTH/207/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/JCNTH/208/orig
Differential Revision: D114936144
@diff-train-skip-merge