Repository navigation
[executorch][muse] Run the MG batching runtime on CudaExecutor - #24007
Merged
Merged
Conversation
Pull Request resolved: #23731 The batching runner and multiplexed worker use the same ServingRuntime, Runner and DecodeFirstScheduler stack on CUDA and MLX; only the executor differs. CudaExecutorConfig now provides model/external-data loading, load mode, session limits, KV dtype, initial pool capacity and backend options to CudaExecutor::create(config). The existing module-based overload remains supported. Both entry points share metadata validation, forward-method discovery, cache construction and graph/weight-sharing setup. A zero config token limit divides the cell pool across resident sessions after reserving its padding row, capped by the published context. The existing Muse backend adapter calls this reusable API and retains only Muse-specific vocabulary/BOS validation and text-only preparation. Remove the separate CUDA backend factory files. Image requests remain rejected for CUDA batching artifacts without a vision path. CMake batching runner/preparation-test targets accept CUDA or MLX, and the CUDA make target builds the shared serving integration. Configuration tests cover automatic and explicit limits, greedy generation parity and invalid/overcommitted configurations. ghstack-source-id: 451855080 @exported-using-ghexport Differential Revision: [D124871959](https://our.internmc.facebook.com/intern/diff/D124871959/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24007
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 225 PendingAs of commit b4fbe74 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: #23731 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/47/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/47/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/46/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/Gasoonjia/47/orig
Differential Revision: D124871959
@diff-train-skip-merge