Skip to content

[executorch][cuda] Expose raw packed steps on CudaExecutor - #24037

Merged
Gasoonjia merged 1 commit into
gh/Gasoonjia/77/origfrom
gh/Gasoonjia/78/orig
Oct 21, 2026
Merged

Gasoonjia merged 1 commit into
gh/Gasoonjia/77/origfrom
gh/Gasoonjia/78/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: #23979 by @Gasoonjia
^ 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/Gasoonjia/78/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/78/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/77/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/78/orig
Differential Revision: D125705711
@diff-train-skip-merge

Pull Request resolved: #23979

DFlash needs the target's verify rows and tapped hidden states from one
forward without the executor's own sampling. Add a RawTargetStep /
execute_raw API and argmax_rows to CudaExecutor, reusing its batch planning,
step declaration and commit, so a model adapter can drive verification the way
the MLX DFlash executor drives its target.
ghstack-source-id: 453099265
@exported-using-ghexport

Differential Revision: [D125705711](https://our.internmc.facebook.com/intern/diff/D125705711/)
@pytorch-bot

pytorch-bot Bot commented Oct 21, 2026

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24037

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.

@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 Oct 21, 2026
@Gasoonjia
Gasoonjia added this pull request to stack #24044 October 21, 2026 06:44
@Gasoonjia
Gasoonjia merged commit 58ca1a3 into main Oct 21, 2026
269 of 285 checks passed
@Gasoonjia
Gasoonjia deleted the gh/Gasoonjia/78/orig branch October 21, 2026 06:48

This branch was successfully deployed

1 active deployment
cadence — 1214c543 Deployed Oct 21, 2026 by pytorchbot via hifi-op-test / hifi4 #34251
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