intel / neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Date Created 2020-07-21 (4 years ago)

Commits 3,747 (last one 23 hours ago)

Stargazers 2,374 (4 this week)

Watchers 32 (0 this week)

Forks 266

License apache-2.0

Ranking

RepositoryStats indexes 640,537 repositories, of these intel/neural-compressor is ranked #22,718 (96th percentile) for total stargazers, and #67,703 for total watchers. Github reports the primary language for this repository as Python, for repositories using this language it is ranked #3,565/131,280.

intel/neural-compressor is also tagged with popular topics, for these it's ranked: large-language-models (#98/1262), knowledge-distillation (#6/172)

Other Information

intel/neural-compressor has 12 open pull requests on Github, 1,636 pull requests have been merged over the lifetime of the repository.

Github issues are enabled, there are 41 open issues and 173 closed issues.

There have been 42 releases, the latest one was published on 2024-12-28 (3 months ago) with the name Intel Neural Compressor Release 3.2.

Homepage URL: https://intel.github.io/neural-compressor/

All Topics

awq fp4 gptq int4 int8 pruning mxformat sparsity sparsegpt auto-tuning smoothquant quantization low-precision large-language-models knowledge-distillation post-training-quantization quantization-aware-training

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

2,367 commits on the default branch (master) since jan '22

Yearly Commits

Commits to the default branch (master) per year

Issue History

Languages

The primary language is Python but there's also others...

updated: 2025-04-17 @ 11:28pm, id: 281528773 / R_kgDOEMfJxQ