Skip to content

Pull requests: vllm-project/compressed-tensors

New pull request New
29 Open 650 Closed
29 Open 650 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[KV cache] Delegate structural reads to the wrapped Cache in QuantizedKVCache
#747 opened Jun 23, 2026 by jethac Loading…
3
[Offload] Key tensors by id
#743 opened Jun 22, 2026 by kylesayrs Collaborator • Draft
4
Add force_local_cache context manager for independent per-rank model loading
#742 opened Jun 22, 2026 by yiliu30 Contributor Loading…
4
[Bugfix] Fix cast_to_fp4 per-rank torch.compile recompilation (#734)
#741 opened Jun 20, 2026 by Yatimai Contributor Loading…
1
8
Add psutil as required dependency
#740 opened Jun 19, 2026 by timkpaine Loading…
2
[Offload] Add print_offload_folder util
#738 opened Jun 18, 2026 by kylesayrs Collaborator Loading…
5
Add XPU support to Buildkite pipeline and scripts
#736 opened Jun 16, 2026 by chensuyue Contributor Loading…
15
Add GemmaConverter for gemma-QAT checkpoints documentation Improvements or additions to documentation
#727 opened Jun 6, 2026 by mgoin Member Loading…
6
Add NVFP4 tensor-block quantization strategy documentation Improvements or additions to documentation
#721 opened Jun 2, 2026 by GillchLee Loading…
22
Add example for converting GSQ/Humming format checkpoints documentation Improvements or additions to documentation
#716 opened May 27, 2026 by mgoin Member Loading…
3
Update documentation link for compression formats
#713 opened May 21, 2026 by dsikka Collaborator Loading…
6
Treat imatrix weight observer as calibration data dependent needs-rebase
#710 opened May 19, 2026 by dshane1903 Loading…
5
[Offload] [1/2] Disambiguate synchronous __setitem__/offload from update_offload
#709 opened May 18, 2026 by kylesayrs Collaborator Loading…
2
[Offload] [2/2] Better abstractions for updating parameters
#703 opened May 10, 2026 by kylesayrs Collaborator Loading…
19
[Offload] use weakref.finalize to handle shared tensor deletion
#698 opened May 1, 2026 by dichn Loading…
1
19
[match] optimized match_named_modules
#697 opened Apr 29, 2026 by brian-dellabetta Collaborator Loading…
1
6
[Bugfix] Do not throw "unexpected non-targeted tensor" validation error for ignored tensors
#692 opened Apr 28, 2026 by kylesayrs Collaborator Loading…
1
[Converters] Support multiple converters documentation Improvements or additions to documentation needs-rebase
#690 opened Apr 27, 2026 by kylesayrs Collaborator Loading…
16
feat: validate shared memory segment limits before CPU offloading
#688 opened Apr 27, 2026 by kylesayrs Collaborator Loading…
6
Add MixFP4 compressed tensor format
#687 opened Apr 27, 2026 by revollllt Loading…
18
fix: use file reference counting to handle shared tensor deletion needs-rebase
#684 opened Apr 18, 2026 by hieusats • Draft
1 of 3 tasks
1
17
[offload] DiskCache.clean_offload_dir needs-rebase
#678 opened Apr 10, 2026 by brian-dellabetta Collaborator • Draft
19
[QuantizationMetadata] update for missing qparams and module attributes needs-rebase
#669 opened Apr 8, 2026 by brian-dellabetta Collaborator Loading…
13
[Misc] [Offload] Update typehints, add docstrings quality-failed
#622 opened Mar 7, 2026 by kylesayrs Collaborator Loading…
17
[Offload] Add stats tracker for debugging/ performance tuning model device movement documentation Improvements or additions to documentation needs-rebase
#615 opened Mar 4, 2026 by kylesayrs Collaborator Loading…
27
ProTip! Updated in the last three days: updated:>2026-06-19.