Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
43 Open 951 Closed
43 Open 951 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

Add MSE vs MinMax observer comparison tests
#2110 opened Dec 11, 2025 by GOavi101 Loading…
8
Fix deprecated torch_dtype usage in transformers loading
#2109 opened Dec 11, 2025 by jangel97 Loading…
4
[Bug fix] fix Qwen3VLMoe
#2104 opened Dec 9, 2025 by Wangzheee Loading…
5
add kv quant example autoround For any PR / issue related to autoround support
#2100 opened Dec 5, 2025 by mengniwang95 Loading…
12
[Utils] Delete deprecated utilities
#2098 opened Dec 5, 2025 by kylesayrs • Draft
2
Linearize gpt_oss model and add separate example to qunatize it to w4a8
#2091 opened Dec 3, 2025 by isharif168 Loading…
14
feat: add importance-aware mixed-precision quantization
#2083 opened Dec 2, 2025 by wangwenmingaa Loading…
7
[test] add e2e test for qwen3 moe w4a16 ready When a PR is ready for review
#2071 opened Nov 25, 2025 by HDCharles • Draft
7
[Performance] Batched calibration ready When a PR is ready for review
#2054 opened Nov 20, 2025 by kylesayrs Loading…
15
[Misc] Remove is_moe_model ready When a PR is ready for review
#2053 opened Nov 20, 2025 by kylesayrs Loading…
3
Testing Clean-up
#2045 opened Nov 18, 2025 by dsikka • Draft
1
Modernize transformers module with type hints and generic types
#2034 opened Nov 14, 2025 by sugatmahanti Loading…
15
Support wInt4aFp8 for moe
#2027 opened Nov 12, 2025 by Wangzheee Loading…
6
[Sequential Onloading] Support onloading and offloading frozen dataclasses
#2016 opened Nov 10, 2025 by kylesayrs Loading…
4
[TypeHint] Fix format_calibration_data type hint
#2012 opened Nov 10, 2025 by kylesayrs Loading…
5
Implement propagate_error argument ready When a PR is ready for review
#2008 opened Nov 10, 2025 by kylesayrs Loading…
8
Granite4 FP8 Block Quantization
#2001 opened Nov 6, 2025 by krishnateja95 Loading…
22
[Kimi Linear] FP8 Example
#1986 opened Oct 31, 2025 by dsikka • Draft
1
[AWQ] Allow users to disable quantization during AWQ
#1973 opened Oct 28, 2025 by brian-dellabetta • Draft
3
[AWQ] Generalize AWQ quantization ready When a PR is ready for review
#1961 opened Oct 22, 2025 by kylesayrs Loading…
4 tasks done
1
35
[Oneshot] Add validation for empty dataset and enhance oneshot function parameters
#1957 opened Oct 21, 2025 by ArkaSanka Loading…
@ArkaSanka
23
[Autowrapper] Trace vision tower for better offloading
#1948 opened Oct 18, 2025 by kylesayrs • Draft
1
[Observers] Change MSE global scale objective function
#1935 opened Oct 14, 2025 by kylesayrs • Draft
1
[Attention] Support FP4 attention quantization nvfp4 For any PR / issue related to NVFP4 support
#1924 opened Oct 14, 2025 by kylesayrs Loading…
3
add gpt oss nvfp4 example
#1885 opened Sep 30, 2025 by shanjiaz • Draft
1
ProTip! no:milestone will show everything without a milestone.