Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
40 Open 556 Closed
40 Open 556 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Tests] GPTQ Actorder Resolution Tests
#1468 opened May 22, 2025 by kylesayrs • Draft
Removed RecipeTuple class ready When a PR is ready for review
#1460 opened May 21, 2025 by shanjiaz Loading…
@shanjiaz
2
Fix missing logs when calling oneshot ready When a PR is ready for review
#1446 opened May 19, 2025 by kelkelcheng Loading…
9
oneshot entrypoint update ready When a PR is ready for review
#1445 opened May 17, 2025 by ved1beta Loading…
10
AWQModifier fast resolve mappings, better logging
#1444 opened May 16, 2025 by brian-dellabetta • Draft
1 task
1
[Research] Llama4 AutoWrapper + Onloading
#1438 opened May 16, 2025 by kylesayrs • Draft
2
[NVFp4] Activation Support
#1437 opened May 15, 2025 by dsikka • Draft
Initial implementation for the docs site and setup for LLM Compressor
#1436 opened May 15, 2025 by markurtz Loading…
@markurtz
4
[WIP][AWQ] Support accumulation for reduced memory usage
#1435 opened May 15, 2025 by kylesayrs • Draft
13
[GPTQ] Change actorder default to "static"
#1425 opened May 12, 2025 by kylesayrs Loading…
3
Use model compression pathways ready When a PR is ready for review
#1419 opened May 8, 2025 by kylesayrs Loading…
3
[WIP][Tracing] Code AutoWrapper
#1411 opened May 4, 2025 by kylesayrs • Draft
validation check added
#1407 opened May 1, 2025 by ved1beta Loading…
1
6
Add warning for non-divisible group quantization ready When a PR is ready for review
#1401 opened Apr 29, 2025 by kylesayrs Loading…
4
[WIP][Testing] Add VL e2e tests
#1400 opened Apr 29, 2025 by kylesayrs • Draft
1
[Tracing] Trace with eager attention
#1392 opened Apr 27, 2025 by kylesayrs Loading…
1
[Tracing] Autowrap methods by name
#1390 opened Apr 27, 2025 by kylesayrs • Draft
1
[Tracing] Raise _is_compiling_flag while tracing ready When a PR is ready for review
#1388 opened Apr 27, 2025 by kylesayrs Loading…
2
[WIP] Recipe model_dump fixes
#1379 opened Apr 23, 2025 by rahul-tuli • Draft
@rahul-tuli
Enhance save_pretrained
#1376 opened Apr 23, 2025 by rahul-tuli • Draft
@rahul-tuli
9
[Experimental] Mistral-format FP8 quantization
#1359 opened Apr 16, 2025 by mgoin • Draft
1
Add traceable mistral and mistral3 classes
#1343 opened Apr 9, 2025 by anmarques • Draft
4
[Tracing] Allow torch.Sizes to be iterated
#1308 opened Apr 1, 2025 by kylesayrs Loading…
3
[Performance] Sequential onloading ready When a PR is ready for review
#1263 opened Mar 18, 2025 by kylesayrs Loading…
@kylesayrs
14
[WIP] [Design] LLMCompressor Class
#1256 opened Mar 15, 2025 by kylesayrs • Draft
25
ProTip! no:milestone will show everything without a milestone.