Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
44 Open 445 Closed
44 Open 445 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] Fix oneshot + finetune test by passing splits to oneshot ready When a PR is ready for review
#1316 opened Apr 2, 2025 by kylesayrs Loading…
1
Fix Multi-Context Manager Syntax for Python 3.9 Compatibility ready When a PR is ready for review
#1313 opened Apr 2, 2025 by rahul-tuli Loading…
1
3
bugfix kv cache quantization with ignored layers
#1312 opened Apr 1, 2025 by brian-dellabetta • Draft
2
Update nm-actions/changed-files to v1.16.0 ready When a PR is ready for review
#1311 opened Apr 1, 2025 by dbarbuzzi Loading…
1
[Tracing] Remove TraceableWhisperForConditionalGeneration
#1310 opened Apr 1, 2025 by kylesayrs Loading…
1
[NVFP4][WIP]: Add FP4 Support
#1309 opened Apr 1, 2025 by dsikka • Draft
1
[Tracing] Allow torch.Sizes to be iterated
#1308 opened Apr 1, 2025 by kylesayrs Loading…
1
[Tracing] Better runtime error messages
#1307 opened Apr 1, 2025 by kylesayrs Loading…
2
Use align_module_device util
#1298 opened Mar 29, 2025 by kylesayrs Loading…
1
Update tests
#1297 opened Mar 28, 2025 by dsikka • Draft
1
Reduce SmoothQuant Repr ready When a PR is ready for review
#1289 opened Mar 27, 2025 by kylesayrs Loading…
2
[BugFix] Multi-gpu temp bug fix ready When a PR is ready for review
#1286 opened Mar 26, 2025 by horheynm • Draft
@dsikka
3
Smoothquant typehinting and onloading context ready When a PR is ready for review
#1285 opened Mar 26, 2025 by kylesayrs Loading…
1
Pipeline Extraction
#1279 opened Mar 24, 2025 by kylesayrs • Draft
4
[BugFix] Directly Convert Modifiers to Recipe Instance ready When a PR is ready for review
#1271 opened Mar 20, 2025 by rahul-tuli Loading…
@rahul-tuli
8
[Tests] Add mark skip for GPU ready When a PR is ready for review
#1264 opened Mar 18, 2025 by kylesayrs Loading…
@kylesayrs
3
[Performance] Sequential onloading ready When a PR is ready for review
#1263 opened Mar 18, 2025 by kylesayrs Loading…
@kylesayrs
14
fix lm eval test reproducbility issues
#1260 opened Mar 17, 2025 by brian-dellabetta Loading…
4
[WIP] [Design] LLMCompressor Class
#1256 opened Mar 15, 2025 by kylesayrs • Draft
25
[Transforms] Enable transforms to be applied to weights during quantization
#1243 opened Mar 11, 2025 by dsikka • Draft
1
[Quantization] Channel-wise Output Activation Quantization for Attention QKV Modules + KV-cache channel quantization ready When a PR is ready for review
#1233 opened Mar 7, 2025 by horheynm • Draft
3
[Callbacks][Docs] Add docstrings to saving functions ready When a PR is ready for review
#1201 opened Feb 26, 2025 by kylesayrs Loading…
2
[Callbacks] Merge on_event with on_update, remove MagnitudePruningModifier.leave_enabled ready When a PR is ready for review
#1199 opened Feb 26, 2025 by kylesayrs Loading…
@kylesayrs
[Utils] Replace preserve_attr with patch_attr ready When a PR is ready for review
#1187 opened Feb 24, 2025 by kylesayrs Loading…
@kylesayrs
7
AWQ Modifier Support
#1177 opened Feb 19, 2025 by brian-dellabetta Loading…
23
ProTip! Updated in the last three days: updated:>2025-03-30.