Repository navigation
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24947
Note: Links to docs will display an error until the docs builds have been completed. ❌ 132 New Failures, 3 Cancelled Jobs, 7 Unrelated Failures, 10 Unclassified FailuresAs of commit dbcb2e1 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. |
meta-cla
Bot
added
the
CLA Signed
This was referenced Nov 12, 2026
--gguf excluded --layers because every GGUF tensor must name a parameter, and a truncated model has none for the later blocks. gguf_to_hf and load_gguf now take truncated=True to skip the blocks past the model's last layer, and the export passes it when --layers is set. That exports a few layers of a large GGUF checkpoint to test the lowering quickly. Without the flag, a tensor that names no parameter still raises.
metascroy
force-pushed
the
offgraph-kv-gguf-layers
branch
from
November 14, 2026 00:18
0e98e55 to
dbcb2e1
Compare
metascroy
force-pushed
the
offgraph-kv-transformers-compat
branch
from
November 14, 2026 00:18
ea18142 to
c399e30
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
--ggufexcluded--layers, because every GGUF tensor must name a parameter and a truncated model has none for the later blocks.gguf_to_hfandload_ggufnow taketruncated=Trueto skip blocks past the model's last layer, and the export passes it when--layersis set. That exports a few layers of a large GGUF checkpoint to test the lowering quickly. Without the flag, a tensor that names no parameter still raises.Test plan
test_gguf_hf.py: a truncated model skips later blocks and still rejects unknown names.test_export_hf_llm.py: a 1-layer model loaded from a 2-layer GGUF matches the reference cut to one layer exactly.Authored with Claude Code.