- Notifications
You must be signed in to change notification settings - Fork401
Pull requests: vllm-project/llm-compressor
Author
Uh oh!
There was an error while loading.Please reload this page.
Label
Uh oh!
There was an error while loading.Please reload this page.
Projects
Uh oh!
There was an error while loading.Please reload this page.
Milestones
Uh oh!
There was an error while loading.Please reload this page.
Reviews
Assignee
Assigned to nobodyLoading
Uh oh!
There was an error while loading.Please reload this page.
Sort
Pull requests list
Add support for passing a custom DataLoader to oneshot()
#2390 openedFeb 20, 2026 bySorenDreanoLoading…
perf: make MSE observer compatible with torch.compile (dual-path implementation) readyWhen a PR is ready for review
#2384 openedFeb 18, 2026 byBias92Loading…
feat: add Qwen3.5 MoE calibration module documentationImprovements or additions to documentation nvfp4For any PR / issue related to NVFP4 support qwenFor any PR / issue related to Qwen support readyWhen a PR is ready for review
#2383 openedFeb 18, 2026 bySehyoLoading…
[Docs] Reorganize + Additional Guides documentationImprovements or additions to documentation readyWhen a PR is ready for review
#2379 openedFeb 17, 2026 bydsikkaLoading…
[Offloading] Support Disk Offloading documentationImprovements or additions to documentation readyWhen a PR is ready for review
#2373 openedFeb 17, 2026 bykylesayrsLoading…
[GPTQ] Move modifier to top-level for consistent folder structure documentationImprovements or additions to documentation needs-rebase readyWhen a PR is ready for review
#2368 openedFeb 16, 2026 bydik654Loading…
add qwen3 vl autoround example documentationImprovements or additions to documentation readyWhen a PR is ready for review
#2357 openedFeb 12, 2026 byxin3heLoading…
Add model_free_ptq example for glm 4.6 block fp8 documentationImprovements or additions to documentation
#2343 openedFeb 10, 2026 bymgoinLoading…
[MoE] MiniMax-M2/M2.1 calibration follow-up documentationImprovements or additions to documentation readyWhen a PR is ready for review
#2335 openedFeb 6, 2026 byLudovicoYINLoading…
Add GSM8K evaluation script and AWQ+FP8 results documentationImprovements or additions to documentation readyWhen a PR is ready for review
#2330 openedFeb 4, 2026 byrtj1Loading…
[AWQ] Add option to consider smooth layer quantization in scale search needs-rebase
#2323 openedJan 31, 2026 byRamshankar07Loading…
Benchmark torch.compile optimization for GPTQ readyWhen a PR is ready for review
#2320 openedJan 31, 2026 bycolldata79Loading…
Add AFMOE mappings for awq and smoothquant needs-rebase readyWhen a PR is ready for review
#2316 openedJan 30, 2026 bybartowski1182Loading…
Refactor Matching Logic to Use compressed-tensors Utilities needs-rebase readyWhen a PR is ready for review
#2284 openedJan 24, 2026 byEtelisLoading…
[Docs][Examples] Add MoE Guide and remove finetune examples documentationImprovements or additions to documentation needs-rebase readyWhen a PR is ready for review
#2281 openedJan 23, 2026 bydsikkaLoading…
[WIP][Examples] model_free_ptq of nvidia/DeepSeek-R1-NVFP4 documentationImprovements or additions to documentation
#2228 openedJan 13, 2026 bybrian-dellabetta • Draft
5 of 6 tasks
[AWQ] Option to disable quantization awqFor any issue / PR related to AWQ support documentationImprovements or additions to documentation needs-rebase readyWhen a PR is ready for review
#2206 openedJan 8, 2026 bybrian-dellabettaLoading…
9 of 10 tasks
Refactor gpt oss quantization use all expert quantization documentationImprovements or additions to documentation readyWhen a PR is ready for review
#2164 openedDec 21, 2025 bysaraswatmksLoading…
ProTip! Find all pull requests that aren't related to any open issues with-linked:issue.