Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
45 Open 1,021 Closed
45 Open 1,021 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

[Examples] Correct out-of-date warning for kv cache examples ready When a PR is ready for review
#2209 opened Jan 9, 2026 by kylesayrs Loading…
3
[AWQ] option to disable quantization
#2206 opened Jan 8, 2026 by brian-dellabetta • Draft
1
5
Add batch token statistics logging to LengthAwareSampler ready When a PR is ready for review
#2204 opened Jan 8, 2026 by jwpark33 Loading…
9
Add NPU support.
#2200 opened Jan 8, 2026 by menogrey Loading…
6
[Bugfix] Fix data_collator default docstring ready When a PR is ready for review
#2197 opened Jan 7, 2026 by kylesayrs Loading…
7
[WIP] Memoryless observers for weights
#2196 opened Jan 7, 2026 by kylesayrs • Draft
6
Switch the pytorch tests to run on the L4 runners ready When a PR is ready for review
#2195 opened Jan 7, 2026 by dhuangnm Loading…
4
[AWQ] speed improvements awq For any issue / PR related to AWQ support enhancement New feature or request ready When a PR is ready for review
#2188 opened Jan 5, 2026 by HDCharles • Draft
15
fix: suppress tokenizer parallelism warning in oneshot
#2183 opened Jan 4, 2026 by majiayu000 Loading…
1
8
[WIP] [Audio] Qwen2 Audio Example
#2177 opened Dec 31, 2025 by kylesayrs • Draft
6
Minimax-M2 / M2.1 calibration
#2171 opened Dec 28, 2025 by mratsim Loading…
17
Added GLM Modeling
#2170 opened Dec 27, 2025 by phaelon74 Loading…
39
support AutoRound NVFP4 scheme autoround For any PR / issue related to autoround support nvfp4 For any PR / issue related to NVFP4 support ready When a PR is ready for review
#2169 opened Dec 26, 2025 by xin3he Loading…
30
Refactor gpt oss quantization use all expert quantization
#2164 opened Dec 21, 2025 by saraswatmks Loading…
1
24
[Offload] Switch to torch offloader from accelerate
#2148 opened Dec 18, 2025 by kylesayrs • Draft
8
[TorchOffloader] Code Cleanup
#2147 opened Dec 18, 2025 by kylesayrs • Draft
6
[Tracing] Dispatch after tracing ready When a PR is ready for review
#2146 opened Dec 17, 2025 by kylesayrs Loading…
3
[Args] Shuffle data samples by default ready When a PR is ready for review
#2144 opened Dec 17, 2025 by kylesayrs Loading…
8
[Bugfix] Improve pipeline inference ready When a PR is ready for review
#2131 opened Dec 15, 2025 by kylesayrs Loading…
5
[Examples] QwenOmni Example ready When a PR is ready for review
#2125 opened Dec 14, 2025 by kylesayrs Loading…
1
12
[Misc] Better debugging and guards to autowrapping ready When a PR is ready for review
#2124 opened Dec 14, 2025 by kylesayrs Loading…
7
[Bug fix] fix Qwen3VLMoe
#2104 opened Dec 9, 2025 by Wangzheee Loading…
9
[Utils] Delete deprecated utilities
#2098 opened Dec 5, 2025 by kylesayrs Loading…
4
feat: add importance-aware mixed-precision quantization
#2083 opened Dec 2, 2025 by wangwenmingaa Loading…
8
[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
ProTip! Follow long discussions with comments:>50.