Repository navigation
[executorch][ci] Test Muse Glimmer batching on CUDA in OSS CI - #24010
Merged
Merged
Conversation
Pull Request resolved: #23818 Build and test Muse Glimmer CUDA batching in OSS CI through the shared serving APIs. The unit job builds the normal runner/worker and explicitly enables the default-OFF MUSE_GLIMMER_BUILD_CI_SMOKE target. The e2e batching mode builds and runs this correctness-only workload with five staggered requests. Require all requests accepted, exact prompt/completion budgets, length completion and successful distinct-session executor steps so serial execution cannot pass as batching coverage. Keep private reusable request control, validation, prompts and batch-owner evidence separate from performance reporting. Smoke reuses ServingRuntime, Runner, DecodeFirstScheduler and the backend executor, disables stop tokens for the exact budget, and has no measurement output. CPU helper regressions cover capacity/overflow validation, successful distinct owners, failed executor calls, exact completion and configure/build failure propagation. Keep the server launcher smoke and existing non-batching variants. Workflow filters and gates explicitly select correctness/helper sources and tests. ghstack-source-id: 451855098 @exported-using-ghexport Differential Revision: [D124871963](https://our.internmc.facebook.com/intern/diff/D124871963/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24010
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 373 PendingAs of commit efa5c01 with merge base 897d28f ( UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
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
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: #23818 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/58/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/58/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/49/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/58/orig
Differential Revision: D124871963
@diff-train-skip-merge