Skip to content

Pull requests: vllm-project/llm-compressor

New pull request New
37 Open 320 Closed
37 Open 320 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

Update examples to only load required number of samples from dataset
#1118 opened Jan 31, 2025 by kylesayrs • Draft
1
[WIP] Support Batch Size for OneShot
#1117 opened Jan 30, 2025 by kylesayrs • Draft
4
Remove empty cache call from calibration forward
#1114 opened Jan 29, 2025 by kylesayrs • Draft
1
@kylesayrs
5
[VLM] Qwen 2.5 VL ready When a PR is ready for review
#1113 opened Jan 29, 2025 by kylesayrs Loading…
@kylesayrs
1
[Oneshot Refactor] Main refactor
#1110 opened Jan 28, 2025 by horheynm Loading…
1
[Oneshot refactor] Refactor initialize_model_from_path ready When a PR is ready for review
#1109 opened Jan 28, 2025 by horheynm Loading…
1
[Oneshot Refactor] Rename get_shared_processor_src to get_processor_from_model ready When a PR is ready for review
#1108 opened Jan 28, 2025 by horheynm Loading…
@horheynm
3
Implement lazy loading for traceable models ready When a PR is ready for review
#1105 opened Jan 28, 2025 by kylesayrs Loading…
@kylesayrs
10
[Oneshot Refactor] dataclass Arguments ready When a PR is ready for review
#1103 opened Jan 27, 2025 by horheynm Loading…
24
Add compressed-tensors appropriate code from llm-compressor
#1098 opened Jan 24, 2025 by horheynm Loading…
1
[WIP] [Audio] People's Speech dataset and tracer tool
#1086 opened Jan 20, 2025 by kylesayrs • Draft
2
[WIP] Fix hessian memory requirements
#1084 opened Jan 20, 2025 by kylesayrs • Draft
1
[Audio] Qwen Audio Example
#1082 opened Jan 19, 2025 by kylesayrs • Draft
Add group act order case to lm_eval test
#1080 opened Jan 17, 2025 by dsikka • Draft
1
[Research] Custom Deepseek Routing
#1070 opened Jan 14, 2025 by kylesayrs • Draft
1
[Test Run] Oneshot refactor + hfquantizer
#1055 opened Jan 10, 2025 by horheynm • Draft
1
[Oneshot] Oneshot Refactor ready When a PR is ready for review
#1041 opened Jan 7, 2025 by horheynm Loading…
22
[BugFix] FSDP script script bug fix ready When a PR is ready for review
#1040 opened Jan 7, 2025 by horheynm Loading…
3
Replace LayerCompressor with HooksMixin ready When a PR is ready for review
#1038 opened Jan 6, 2025 by kylesayrs Loading…
@kylesayrs
3
Extend disable_hooks to keep subsets ready When a PR is ready for review
#1023 opened Jan 1, 2025 by kylesayrs Loading…
@kylesayrs
3
Remove missing weights silencers in favor of HFQuantizer solution
#1017 opened Dec 28, 2024 by kylesayrs • Draft
3
[Test Run] Merge of tests using AutoModelForCausalLM - transformers latest release
#1011 opened Dec 23, 2024 by horheynm • Draft
1
Dataset Processing Args
#1006 opened Dec 20, 2024 by kylesayrs • Draft
1
Dataset split fallbacks
#953 opened Dec 4, 2024 by kylesayrs • Draft
3
Move SparseGPTModifier location with backwards compatibility
#919 opened Nov 16, 2024 by kylesayrs • Draft
@kylesayrs
3
ProTip! Updated in the last three days: updated:>2025-01-29.