Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
40 Open 899 Closed
40 Open 899 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

Granite4 FP8 Block Quantization
#2001 opened Nov 6, 2025 by krishnateja95 Loading…
11
Add Intel AutoRound algorithm support ready When a PR is ready for review
#1994 opened Nov 5, 2025 by yiliu30 Loading…
3 tasks
1
@yiliu30
33
Modernize metrics module with type hints and generic types
#1993 opened Nov 5, 2025 by sugatmahanti Loading…
15
[model_free_ptq] NVFP4A16
#1988 opened Nov 3, 2025 by kylesayrs • Draft
1
[Kimi Linear] FP8 Example
#1986 opened Oct 31, 2025 by dsikka • Draft
1
[AWQ] allow for use of model-wide kwargs cache
#1985 opened Oct 30, 2025 by brian-dellabetta • Draft
1
[MoE] Clean up imports, add qwen3_moe_vl, change logger level ready When a PR is ready for review
#1981 opened Oct 29, 2025 by kylesayrs Loading…
14
[AWQ] Allow users to disable quantization during AWQ
#1973 opened Oct 28, 2025 by brian-dellabetta • Draft
3
[WIP] Generalize AWQ quantization
#1961 opened Oct 22, 2025 by kylesayrs • Draft
2
Adding new MoE e2e tests fp8 For any issue / PR related to FP8 support nvfp4 For any PR / issue related to NVFP4 support ready When a PR is ready for review wNa16 Anything related to weight-only int-quantized support
#1960 opened Oct 22, 2025 by HDCharles Loading…
13
[Oneshot] Add validation for empty dataset and enhance oneshot function parameters
#1957 opened Oct 21, 2025 by ArkaSanka Loading…
@ArkaSanka
13
[Autowrapper] Trace vision tower for better offloading
#1948 opened Oct 18, 2025 by kylesayrs • Draft
1
[MXFP4] Support
#1938 opened Oct 15, 2025 by dsikka • Draft
1
[Observers] Change MSE global scale objective function
#1935 opened Oct 14, 2025 by kylesayrs • Draft
1
AI Fix for: Create AWQ guide for llm-docs
#1932 opened Oct 14, 2025 by shanaya-Gupta Loading…
1
7
[Attention] Support FP4 attention quantization nvfp4 For any PR / issue related to NVFP4 support
#1924 opened Oct 14, 2025 by kylesayrs Loading…
3
Add: File Based Caching for lm_eval tests
#1900 opened Oct 6, 2025 by rahul-tuli • Draft
8
[Training] Fix tokenizer attribute of SessionMixin ready When a PR is ready for review
#1895 opened Oct 1, 2025 by kylesayrs Loading…
4
add gpt oss nvfp4 example
#1885 opened Sep 30, 2025 by shanjiaz • Draft
1
Add awq activation fp8 support in loss compute
#1873 opened Sep 27, 2025 by Bluedyson Loading…
4
[Logging] clean up CompressionLogger verbosity ready When a PR is ready for review
#1861 opened Sep 23, 2025 by brian-dellabetta Loading…
MSE observer for NVFP4
#1840 opened Sep 17, 2025 by shubhra Loading…
26
Updating base.py (parallel calibration and model #1809)
#1837 opened Sep 17, 2025 by aashvgit Loading…
7
Add file to linearize and quantize the gpt-oss models
#1831 opened Sep 17, 2025 by shubhra Loading…
18
[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…
9
ProTip! Follow long discussions with comments:>50.