Repository navigation
[executorch][cuda] Test CudaExecutor on every step width up to 65 - #24011
Merged
Merged
Conversation
Pull Request resolved: #23819 CudaExecutor chooses the narrowest static forward_{N} that holds a step, pads unused rows into the KV scratch cell without returning their logits, and uses forward_others with slicing for wider steps. Extend the toy artifact to the Muse-sized method set forward_{1,2,4,...,64} plus forward_others, with eight independently referenced prompts and continuations. EveryStepWidthUpTo65MatchesEagerGreedy covers every width 1..65 plus 96 and 97, shuffled repeatedly, with CUDA graphs both on and off. Mix sequence owners and chunk lengths, teacher-force eager reference histories, and vary which chunks request output. Assert the selected method sequence, exact output ownership/count and eager greedy token at each requested position. This is correctness coverage of static padding, dynamic widths and slicing, without serving performance reporting. ghstack-source-id: 451855103 @exported-using-ghexport Differential Revision: [D125110873](https://our.internmc.facebook.com/intern/diff/D125110873/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24011
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 191 PendingAs of commit 0be3c22 with merge base 897d28f ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
shoumikhin
approved these changes
Oct 20, 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
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #23819 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/59/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/59/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/58/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/59/orig
Differential Revision: D125110873
@diff-train-skip-merge