Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
43 Open 1,140 Closed
43 Open 1,140 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

[Bugfix] Reduce device movement while checking layer divisibility
#2385 opened Feb 18, 2026 by kylesayrs Loading…
3
perf: make MSE observer compatible with torch.compile (39x speedup) quality-failed
#2384 opened Feb 18, 2026 by Bias92 Loading…
10
feat: add Qwen3.5 MoE calibration module documentation Improvements or additions to documentation nvfp4 For any PR / issue related to NVFP4 support quality-failed qwen For any PR / issue related to Qwen support ready When a PR is ready for review
#2383 opened Feb 18, 2026 by Sehyo Loading…
9
[Docs] Reorganize documentation Improvements or additions to documentation needs-rebase
#2379 opened Feb 17, 2026 by dsikka • Draft
8
[Oneshot] Add validation for empty dataset and enhance oneshot function parameters (Supersedes PR #1957) needs-rebase
#2378 opened Feb 17, 2026 by ArkaSanka • Draft
6
[Qwen3.5 MoE Support] documentation Improvements or additions to documentation quality-failed
#2377 opened Feb 17, 2026 by dsikka • Draft
12
[Tests][e2e] Release memory before running vLLM ready When a PR is ready for review
#2375 opened Feb 17, 2026 by dsikka • Draft
5
[Offloading] Support Disk Offloading documentation Improvements or additions to documentation ready When a PR is ready for review
#2373 opened Feb 17, 2026 by kylesayrs Loading…
6
[GPTQ] Move modifier to top-level for consistent folder structure documentation Improvements or additions to documentation ready When a PR is ready for review
#2368 opened Feb 16, 2026 by dik654 Loading…
7
add qwen3 vl autoround example documentation Improvements or additions to documentation ready When a PR is ready for review
#2357 opened Feb 12, 2026 by xin3he Loading…
7
Add model_free_ptq example for glm 4.6 block fp8 documentation Improvements or additions to documentation
#2343 opened Feb 10, 2026 by mgoin Loading…
6
Improve how we identify and run e2e smoke tests
#2336 opened Feb 6, 2026 by dhuangnm Loading…
8
[MoE] MiniMax-M2/M2.1 calibration follow-up documentation Improvements or additions to documentation ready When a PR is ready for review
#2335 opened Feb 6, 2026 by LudovicoYIN Loading…
12
[GPTQ][ddp] enabling DDP for GPTQ dist Work pertaining to distributed work documentation Improvements or additions to documentation enhancement New feature or request gptq For any PR / issue related to GPTQ support quality-failed ready When a PR is ready for review
#2333 opened Feb 6, 2026 by HDCharles Loading…
33
[AutoRound] Add DP Support
#2331 opened Feb 5, 2026 by yiliu30 Loading…
6
Add GSM8K evaluation script and AWQ+FP8 results documentation Improvements or additions to documentation ready When a PR is ready for review
#2330 opened Feb 4, 2026 by rtj1 Loading…
1
17
Update CODEOWNERS to include modifiers
#2329 opened Feb 4, 2026 by dsikka • Draft
5
[AWQ] Add option to consider smooth layer quantization in scale search needs-rebase
#2323 opened Jan 31, 2026 by Ramshankar07 Loading…
53
Benchmark torch.compile optimization for quantization ready When a PR is ready for review
#2320 opened Jan 31, 2026 by colldata79 Loading…
19
Update vLLM GPU Utilization
#2319 opened Jan 30, 2026 by dsikka • Draft
2
Add AFMOE mappings for awq and smoothquant needs-rebase ready When a PR is ready for review
#2316 opened Jan 30, 2026 by bartowski1182 Loading…
13
move smoothquant to transforms documentation Improvements or additions to documentation needs-rebase ready When a PR is ready for review
#2314 opened Jan 30, 2026 by Etelis Loading…
1
13
Refactor Matching Logic to Use compressed-tensors Utilities needs-rebase ready When a PR is ready for review
#2284 opened Jan 24, 2026 by Etelis Loading…
1
26
[Observers] Allow for case when weight shape and block size are not evenly divisble ready When a PR is ready for review
#2283 opened Jan 23, 2026 by brian-dellabetta Loading…
2 tasks done
16
[Docs][Examples] Add MoE Guide and remove finetune examples documentation Improvements or additions to documentation needs-rebase ready When a PR is ready for review
#2281 opened Jan 23, 2026 by dsikka Loading…
27
ProTip! What’s not been updated in a month: updated:<2026-01-18.