Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
38 Open 769 Closed
38 Open 769 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

Allow e2e tests to run vllm in a separate python environment
#1802 opened Sep 5, 2025 by dhuangnm Loading…
13
Consolidate example script tests into single parametrized test
#1801 opened Sep 5, 2025 by fynnsu Loading…
21
[Entrypoints] initialize processor error handling ready When a PR is ready for review
#1796 opened Sep 3, 2025 by brian-dellabetta Loading…
1
11
make transformer fix backward compatible
#1794 opened Sep 2, 2025 by shanjiaz Loading…
8
add support for per-head attention quantization
#1791 opened Sep 2, 2025 by eldarkurtic Loading…
5
Fix negative activation values in awq scale calculation ready When a PR is ready for review
#1788 opened Aug 29, 2025 by fynnsu Loading…
11
Updating API docs ready When a PR is ready for review
#1787 opened Aug 29, 2025 by aireilly Loading…
15
[QuantizationFormat] Remove code inferring format ready When a PR is ready for review
#1786 opened Aug 29, 2025 by dsikka Loading…
9
Recovered skipped w8a8 compression related tests ready When a PR is ready for review
#1785 opened Aug 29, 2025 by shanjiaz • Draft
3
[MXFP4] Add mxfp4 support
#1783 opened Aug 28, 2025 by dsikka • Draft
1
[Transform] Support separating v and u transforms of quip ready When a PR is ready for review
#1782 opened Aug 27, 2025 by kylesayrs Loading…
15
[Transform] Spinquant R3 ready When a PR is ready for review
#1778 opened Aug 27, 2025 by kylesayrs Loading…
4
[Multi-modifier] Support scoped application of quantization config/status
#1772 opened Aug 21, 2025 by brian-dellabetta • Draft
4 of 6 tasks
1
[MoE] MoE Calibration with calibrate_all_experts
#1760 opened Aug 19, 2025 by kylesayrs • Draft
15
[Tests] Add recovery-based validation to LM-Eval tests
#1750 opened Aug 18, 2025 by rahul-tuli • Draft
2 of 7 tasks
5
[Tracing] Support Cohere Vision, Decouple vision tower from first layer ready When a PR is ready for review
#1710 opened Aug 6, 2025 by kylesayrs Loading…
8
[WIP] [MoE] GPT OSS
#1705 opened Aug 5, 2025 by kylesayrs • Draft
11
[MoE] Add conditional expert calibration
#1701 opened Aug 1, 2025 by dichn • Draft
20
[Example] [VLM] Gemma3n
#1696 opened Jul 31, 2025 by kylesayrs • Draft
4
[Autowrapper] Support Gemma3n, autowrapper improvements ready When a PR is ready for review
#1693 opened Jul 30, 2025 by kylesayrs Loading…
7
1686 Logic matching refactor
#1687 opened Jul 28, 2025 by ved1beta Loading…
15
[AWQ] Allow for activation quantization
#1682 opened Jul 24, 2025 by brian-dellabetta • Draft
1
7
add quantization_w4a4_fp4 qwen3 example
#1681 opened Jul 24, 2025 by wangwenmingaa Loading…
7
[KV Cache] support kv cache int8 per channel quantization ready When a PR is ready for review
#1663 opened Jul 19, 2025 by Eviannn Loading…
11
[Transform] Online Rotations
#1651 opened Jul 16, 2025 by kylesayrs • Draft
9
ProTip! Exclude everything labeled bug with -label:bug.