Repository navigation
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24954
Note: Links to docs will display an error until the docs builds have been completed. ❌ 135 New Failures, 3 Cancelled Jobs, 1 Pending, 7 Unrelated Failures, 10 Unclassified FailuresAs of commit 8654920 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:
CANCELLED JOBS - The following jobs were cancelled. Please retry:
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
meta-cla
Bot
added
the
CLA Signed
metascroy
force-pushed
the
offgraph-kv-shared-cache-geometry
branch
from
November 13, 2026 00:57
370c1ae to
03f97b0
Compare
metascroy
changed the base branch from
offgraph-kv-sequence-batch-control
to
offgraph-kv-mg-export
November 13, 2026 00:57
This was referenced Nov 13, 2026
The native LLM runner derived the off-graph KV cache a method needs, its layers from the update_and_attend calls and their windows from the package metadata, in code private to the runner. Move it to the header-only backends/native/runtime/OffGraphCache.h, with the token bound that sizes a ring layer, so a serving executor builds the same cache. The runner is unchanged in behavior.
metascroy
force-pushed
the
offgraph-kv-mg-export
branch
from
November 14, 2026 00:18
e701e1d to
9093078
Compare
metascroy
force-pushed
the
offgraph-kv-shared-cache-geometry
branch
from
November 14, 2026 00:18
03f97b0 to
8654920
Compare
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
The native LLM runner derived the off-graph KV cache a method needs in code private to the runner: layers from the
update_and_attendcalls, windows from the package metadata. This moves it to the header-onlybackends/native/runtime/OffGraphCache.h, along with the token bound that sizes a ring layer, so a serving executor builds the same cache. The runner's behavior is unchanged.Test plan
The runner still verifies golden samples of a sliding-window package and a Muse Glimmer slice.
Authored with Claude Code.