Repository navigation
fix(deps): pin compressed-tensors to 0.18.0 - #36794
Merged
Merged
Conversation
github-actions
Bot
added
the
dependencies
YAMY1234
marked this pull request as ready for review
August 28, 2026 05:47
YAMY1234
requested review from
Fridge003,
ispobock and
merrymercy
as code owners
August 28, 2026 05:47
Collaborator
Author
|
/rerun-test test/registered/unit/layers/quantization/test_compressed_tensors_mixed_precision.py::TestMixedPrecisionFormat.test_linear_scheme_uses_per_group_format test/registered/unit/layers/quantization/test_compressed_tensors_wna16_moe_no_linear.py::TestWNA16MoENoLinearGroup.test_blackwell_auto_rejects_unvalidated_triton_layouts |
mmangkad
approved these changes
Aug 28, 2026
Contributor
|
Results for 🚀 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
SGLang's Base CPU CI installs development dependencies with
--prerelease allow. The unboundedcompressed-tensorsdependency therefore resolved to0.18.1a20260827, which includes the intentional removal of GPTQ group/dynamic activation ordering from vllm-project/compressed-tensors#840.Current SGLang still references
ActivationOrdering.GROUPin its production compressed-tensors WNA16 scheme and retains coverage for legacyactorder="group"configurations. This breaks unrelated PRs during dependency installation and CPU validation:AttributeError: GROUPactorder='group' has been removedModification
Pin the primary SGLang package dependency to
compressed-tensors==0.18.0, the latest stable release that retainsActivationOrdering.GROUPand accepts the existing configuration contract.This is a short-term compatibility pin. A separate follow-up can decide how SGLang should migrate or retire legacy group-actorder checkpoint support before moving to
compressed-tensors>=0.18.1.Validation
python/pyproject.tomland verified the dependency resolves exactly tocompressed-tensors==0.18.0.compressed-tensors==0.18.0wheel and verified it retainsActivationOrdering.GROUP.git diff --checkpasses.Full CI is left to this draft PR.
CI States
Latest PR Test (Base): ❌ Run #33145815123
Latest PR Test (Extra): ❌ Run #33145815055
Latest PR Test (AMD ROCm 7.2): ❌ Run #33145815122