Repository navigation
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24955
Note: Links to docs will display an error until the docs builds have been completed. ❌ 134 New Failures, 7 Unrelated Failures, 10 Unclassified FailuresAs of commit f7656ba 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
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
force-pushed
the
offgraph-kv-publish-context
branch
from
November 13, 2026 00:57
1119461 to
649456f
Compare
This was referenced Nov 13, 2026
A serving runtime sizes its sessions from the context a package publishes, as MLX packages do with get_max_context_len, but native packages carried only the cache geometry. The off-graph export now also writes the model's max_position_embeddings under that name. The wrapper's cache_metadata() becomes metadata(), since it is no longer only the cache's.
metascroy
force-pushed
the
offgraph-kv-publish-context
branch
from
November 14, 2026 00:18
649456f to
f7656ba
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
A serving runtime sizes its sessions from the context a package publishes, as MLX packages do with
get_max_context_len, but native packages carried only the cache geometry. The off-graph export now also writes the model'smax_position_embeddingsunder that name, or the export's--max_seq_lengthfor a config without one. For an off-graph package this is the longest context the model supports; the runtime still sizes its own cache. The wrapper'scache_metadata()becomesmetadata(), since it now carries more than the cache's geometry.Test plan
test_export_hf_llm.pyon transformers 5.0.0rc1 and 5.22.2. A full Muse Glimmer export publishes 131072.Authored with Claude Code.