[Vulkan] Delegate aten.scalar_tensor with exact integer values - #23210
Closed
mergennachin wants to merge 1 commit into
Closed
mergennachin wants to merge 1 commit into
mergennachin wants to merge 1 commit into
Conversation
EXIR leaves scalar_tensor in the ATen dialect, so the partitioner never matched the edge-dialect registration, and the graph builder emitted a name the runtime does not recognize. The op is now registered for both targets, serialized as aten.scalar_tensor.default, and the scalar is uploaded in the output's type so integer values are exact. Scalars that cannot be represented stay on CPU. Fixes #23158 Authored with OpenAI Codex; split planned with Claude Code.
pytorch-bot
Bot
added
the
module: vulkan
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/23210
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit e1ab320 with merge base a318382 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This was referenced Sep 28, 2026
This branch was successfully deployed
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Superseded by #23249, part 10/15 of the ghstack replacement series. The current integration PR is #23254. This PR is closed in favor of the replacement; its previous description and review history are retained.
EXIR leaves scalar_tensor in the ATen dialect, so the partitioner never matched the edge-dialect registration, and the graph builder emitted a name the runtime does not recognize. The op is now registered for both targets, serialized as aten.scalar_tensor.default, and the scalar is uploaded in the output's type so integer values are exact. Scalars that cannot be represented stay on CPU.
Fixes #23158
Part 10/15 of the Vulkan transformer and operator-conformance stack. Depends on #23209; review against the selected base branch. Integration PR: #23162.
Validation: 8 passed, 2 warnings in 45.35s. Lintrunner and git diff --check pass. Native tests use MoltenVK with portable CPU kernels; hardware and SwiftShader CI are pending.
Authored with OpenAI Codex; split planned with Claude Code.
cc @SS-JIA @manuelcandales @digantdesai @cbilgin