Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
92 Open 1,574 Closed
92 Open 1,574 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

[TEST] No-trigger test: .md file change documentation Improvements or additions to documentation two-reviews When a PR requires two reviews
#3009 opened Aug 7, 2026 by rashmigottipati Collaborator Loading…
10
[TEST] No-trigger test: tests/e2e/ change two-reviews When a PR requires two reviews
#3008 opened Aug 7, 2026 by rashmigottipati Collaborator Loading…
8
[TEST] Trigger test: .buildkite/ change two-reviews When a PR requires two reviews
#3007 opened Aug 7, 2026 by rashmigottipati Collaborator Loading…
6
[TEST] Trigger test: src/ change two-reviews When a PR requires two reviews
#3006 opened Aug 7, 2026 by rashmigottipati Collaborator Loading…
8
Update lm_eval test configs: cadence, FP8 block, disable stale
#3004 opened Aug 7, 2026 by kylesayrs Collaborator Loading…
1 of 2 tasks
7
Add native FP8 expert support to REAP two-reviews When a PR requires two reviews
#3003 opened Aug 6, 2026 by ieBoytsov Loading…
8
[Performance] Speed up subgraph tracing - add direct dict lookup for O(1) node membership checks two-reviews When a PR requires two reviews
#2999 opened Aug 4, 2026 by wanadzhar913 Contributor Loading…
10
Avoid CUDA indexing failures in iMatrix grid search updates two-reviews When a PR requires two reviews
#2997 opened Aug 3, 2026 by yasu-oh Loading…
9
Let AWQ mappings absorb scales into a sliced projection awq For any issue / PR related to AWQ support two-reviews When a PR requires two reviews
#2996 opened Aug 3, 2026 by Ar4ikov Loading…
@brian-dellabetta
9
Add layerwise decompression and compression to sequential pipeline quality-failed
#2995 opened Aug 2, 2026 by kylesayrs Collaborator Loading…
5 tasks
6
feat: add Kimi-K3 model definition and quantization example quality-failed
#2994 opened Aug 2, 2026 by kylesayrs Collaborator Loading…
3 tasks
15
feat: resumable model-free PTQ with meta-tensor skip quality-failed
#2993 opened Aug 2, 2026 by kylesayrs Collaborator Loading…
3 tasks
7
[Performance] Speed up subgraph tracing two-reviews When a PR requires two reviews
#2992 opened Aug 2, 2026 by YingqiDuan Loading…
6
[Observer] Triton grid search for the MSE observer
#2991 opened Aug 1, 2026 by Bias92 Contributor • Draft
7
[Bugfix] Do not recurse into container modules in observe/update_qparams two-reviews When a PR requires two reviews
#2990 opened Jul 31, 2026 by Ar4ikov Loading…
10
Fix DDP race condition on HF cached_files two-reviews When a PR requires two reviews
#2988 opened Jul 30, 2026 by rohan9446 Loading…
1
6
INFERENG-9489: Simplify Transformers tests detection using Buildkite if_changed Refactor Code cleanup and/or improvements to existing features two-reviews When a PR requires two reviews
#2983 opened Jul 30, 2026 by rashmigottipati Collaborator Loading…
27
[Kimi-K3] Enable REAP expert pruning with LinearExperts2D
#2980 opened Jul 29, 2026 by KKothuri Contributor • Draft
8
[WIP] [Kimi-K3] needs-rebase quality-failed
#2978 opened Jul 29, 2026 by kylesayrs Collaborator • Draft
19
feat: dynamic memory-aware GPU scheduling for model-free PTQ two-reviews When a PR requires two reviews
#2976 opened Jul 28, 2026 by rohan9446 Loading…
1
54
fix: runtime bugs in recipe validation, autoround, and awq two-reviews When a PR requires two reviews
#2973 opened Jul 25, 2026 by soyr-redhat Contributor Loading…
11
update skills to apply transforms and more custom recipes documentation Improvements or additions to documentation
#2971 opened Jul 24, 2026 by dsikka Collaborator • Draft
6
[Typing] Modernize type hints in logger, datasets, and observers quality-failed two-reviews When a PR requires two reviews
#2960 opened Jul 23, 2026 by arijitroy003 Contributor Loading…
7
Add logging to silently swallowed exceptions in ModifierFactory two-reviews When a PR requires two reviews
#2957 opened Jul 23, 2026 by arijitroy003 Contributor Loading…
9
MSE Observer Enhancement enhancement New feature or request fp8 For any issue / PR related to FP8 support ready When a PR is ready for review two-reviews When a PR requires two reviews
#2950 opened Jul 22, 2026 by Roderick-Wu Collaborator Loading…
29
ProTip! Add no:assignee to see everything that’s not assigned.