Skip to content

Pull requests: vllm-project/llm-compressor

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
Assignee
Filter by who’s assigned
Sort

Pull requests list

Add timing functionality to lm-eval tests
#1346 opened Apr 11, 2025 by ved1beta Loading…
Update test_oneshot_and_finetune.py to use pytest.approx ready When a PR is ready for review
#1339 opened Apr 9, 2025 by markurtz Loading…
Revert transformers version pin
#1338 opened Apr 9, 2025 by AlexanderSing Loading…
[Tracing][Testing] Add tracing tests ready When a PR is ready for review
#1335 opened Apr 8, 2025 by kylesayrs Loading…
[Model] Llama4 Support
#1333 opened Apr 8, 2025 by kylesayrs Draft
[Compression] Update sparsity calculation lifecycle when fetching the compressor ready When a PR is ready for review
#1332 opened Apr 8, 2025 by dsikka Loading…
fix: Make Recipe.model_dump() output compatible with model_validate() ready When a PR is ready for review
#1328 opened Apr 6, 2025 by ved1beta Loading…
bugfix kv cache quantization with ignored layers ready When a PR is ready for review
#1312 opened Apr 1, 2025 by brian-dellabetta Loading…
[NVFP4][WIP]: Add FP4 Support
#1309 opened Apr 1, 2025 by dsikka Draft
[Tracing] Allow torch.Sizes to be iterated
#1308 opened Apr 1, 2025 by kylesayrs Loading…
[Tracing] Better runtime error messages ready When a PR is ready for review
#1307 opened Apr 1, 2025 by kylesayrs Loading…
Use align_module_device util
#1298 opened Mar 29, 2025 by kylesayrs Loading…
Update tests
#1297 opened Mar 28, 2025 by dsikka Draft
Reduce SmoothQuant Repr ready When a PR is ready for review
#1289 opened Mar 27, 2025 by kylesayrs Loading…
[BugFix] Multi-gpu temp bug fix ready When a PR is ready for review
#1286 opened Mar 26, 2025 by horheynm Draft
Smoothquant typehinting and onloading context ready When a PR is ready for review
#1285 opened Mar 26, 2025 by kylesayrs Loading…
Pipeline Extraction
#1279 opened Mar 24, 2025 by kylesayrs Draft
[Tests] Add mark skip for GPU ready When a PR is ready for review
#1264 opened Mar 18, 2025 by kylesayrs Loading…
[Performance] Sequential onloading ready When a PR is ready for review
#1263 opened Mar 18, 2025 by kylesayrs Loading…
fix lm eval test reproducbility issues
#1260 opened Mar 17, 2025 by brian-dellabetta Loading…
ProTip! Exclude everything labeled bug with -label:bug.