Repository navigation
Conversation
BatchControl answers pos() for each sequence, but SequenceControl offered no way to ask where its one sequence stands; only SequenceCache, which a control plane does not include, had length(). Add length() to the face. Every implementation (SequenceCache and MLXSequenceCache) already had it, so this only marks those overrides.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24952
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 170 New Failures, 6 Unrelated Failures, 23 Unclassified FailuresAs of commit ba42f2b with merge base c7f7931 ( NEW FAILURES - The following jobs have failed:
UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Nov 12, 2026
Contributor
Author
|
Superseded: the native executor now serves sessions from a real multi-sequence ggml cache (#25007) instead of adapting the single-sequence cache, so this is no longer needed. |
This branch had an error being 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Stack
Off-graph KV cache for the native ggml engine, through serving Muse Glimmer on it. Review bottom-up; each PR builds and passes its tests on its own.
Summary
BatchControlanswerspos()for each sequence, butSequenceControloffered no way to ask where its one sequence stands; onlySequenceCache, which a control plane does not include, hadlength(). This addslength()to the face. Every implementation (SequenceCache,MLXSequenceCache) already had it, so this only marks those overrides.Test plan
cache_test.cpp: the control face reports the length through commits, rewinds and clears. MLX and CUDA weren't built locally; the change there is theoverridekeyword.Authored with Claude Code.