Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
67 Open 1,297 Closed
67 Open 1,297 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

[AWQ] Fix accuracy on Qwen3.5 attn_output_gate; identity-baseline correctness; non-finite fail-fast awq For any issue / PR related to AWQ support bug Something isn't working enhancement New feature or request qwen For any PR / issue related to Qwen support w4a16
#2630 opened Apr 18, 2026 by juju812 Loading…
5 tasks done
7
[deps] Bump to torch 2.10 enhancement New feature or request ready When a PR is ready for review
#2629 opened Apr 17, 2026 by brian-dellabetta Collaborator Loading…
1 task done
3
[not for merge] Validate linkspector action enhancement New feature or request Refactor Code cleanup and/or improvements to existing features
#2626 opened Apr 16, 2026 by brian-dellabetta Collaborator Loading…
10
[README] Add link to user survey documentation Improvements or additions to documentation ready When a PR is ready for review
#2625 opened Apr 16, 2026 by brian-dellabetta Collaborator Loading…
10
Adding test_group to lm-eval configs enhancement New feature or request fp8 For any issue / PR related to FP8 support nvfp4 For any PR / issue related to NVFP4 support w4a16
#2623 opened Apr 16, 2026 by debroy-rh Loading…
6
Defer weight qparams to epoch end, unify calibration lifecycle
#2621 opened Apr 15, 2026 by HDCharles Collaborator Loading…
2 of 5 tasks
3
test gptq issue [not for land] enhancement New feature or request gptq For any PR / issue related to GPTQ support nvfp4 For any PR / issue related to NVFP4 support quality-failed
#2617 opened Apr 14, 2026 by HDCharles Collaborator Loading…
10
Add actorder support for GPTQ block quantization enhancement New feature or request fp8 For any issue / PR related to FP8 support gptq For any PR / issue related to GPTQ support ready When a PR is ready for review Refactor Code cleanup and/or improvements to existing features
#2616 opened Apr 14, 2026 by rk119 Loading…
1
@HDCharles
13
[Tests] Add transformers v5 modeling tests and clean up import guards qwen For any PR / issue related to Qwen support Refactor Code cleanup and/or improvements to existing features
#2614 opened Apr 13, 2026 by dsikka Collaborator Loading…
9
[not for land] DDP regression tests awq For any issue / PR related to AWQ support documentation Improvements or additions to documentation enhancement New feature or request llama For any PR / issue related to Llama herd support quality-failed qwen For any PR / issue related to Qwen support
#2613 opened Apr 13, 2026 by HDCharles Collaborator Loading…
4 tasks done
17
Add SmoothQuant mappings for Qwen2/3 MoE models qwen For any PR / issue related to Qwen support ready When a PR is ready for review smoothquant For any issue / PR related to SmoothQuant support transforms Related to transforms-based modifiers like SpinQuant and Quip
#2609 opened Apr 12, 2026 by elwhyjay Loading…
@brian-dellabetta
11
fix: support transformers >= 5.0 (TORCH_INIT_FUNCTIONS fallback) bug Something isn't working qwen For any PR / issue related to Qwen support w4a16
#2608 opened Apr 12, 2026 by quivent Loading…
6
refactor: modernize observers module with Python 3.10+ type hints Refactor Code cleanup and/or improvements to existing features
#2607 opened Apr 12, 2026 by elwhyjay Loading…
3 tasks done
5
Fix CI regression on AWQ eval awq For any issue / PR related to AWQ support enhancement New feature or request w4a16
#2606 opened Apr 10, 2026 by HDCharles Collaborator Loading…
6
[oneshot] clean offload_dir during post-processing
#2605 opened Apr 10, 2026 by brian-dellabetta Collaborator • Draft
3 tasks
4
[docs] deepseek v3.2 docs documentation Improvements or additions to documentation ready When a PR is ready for review
#2602 opened Apr 10, 2026 by brian-dellabetta Collaborator Loading…
17
Migrate to pyproject.toml and use dependabot for automatic handling quality-failed
#2600 opened Apr 10, 2026 by dsikka Collaborator • Draft
20
fix: correct TOKENIZERS_PARALLELISM_ENV constant value ready When a PR is ready for review
#2596 opened Apr 10, 2026 by kuishou68 Loading…
1
6
[linkspector] only run action if there are changes to markdown files ready When a PR is ready for review
#2594 opened Apr 9, 2026 by brian-dellabetta Collaborator Loading…
7
[Refactor] Refactor splits to only use the "calibration" split (#2551) ready When a PR is ready for review Refactor Code cleanup and/or improvements to existing features
#2589 opened Apr 8, 2026 by arpitkh101 Loading…
1
24
[save_pretrained] UX improvement for save_compressed=False needs-rebase
#2588 opened Apr 8, 2026 by brian-dellabetta Collaborator Loading…
1 task
10
Observers refactor quality-failed
#2585 opened Apr 8, 2026 by HDCharles Collaborator Loading…
35
[Refactor] Consolidate Intermediate Offloading needs-rebase
#2583 opened Apr 8, 2026 by menogrey Contributor Loading…
@HDCharles
26
[AWQ] [gemma3] remove input layernorm mapping
#2571 opened Apr 6, 2026 by brian-dellabetta Collaborator Loading…
1 task
1
8
[Bugfix] Fix model_free_ptq for models with non-contiguous fused attention layers needs-rebase
#2566 opened Apr 6, 2026 by RobTand Loading…
6 tasks done
8
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.