Analyze intel/neural-compressor
neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX RuntimePython
Apache License 2.0
Overview
Summary of the overall repo health
Adoption
Metrics on how many people know and interact with the repo
Stars
1,932
Open Issues
52
Forks
238
Top 1% by stars on GitHub
Contribution
Top Contributors
Top 10 contributors to the repo and their shares
Commits Properties
Metrics showing the quality of commits distribution
Bus Factor
Serious Ratio
Bus factor is less than 10
Diversity
Geo Distribution
Top locations by number of contributors and commits
Org Distribution
Top organizations contributing to the repo
Governance
Community governance docs check
Description |
---|
Website |
Code of Conduct |
Contributing.md |
Issue Template |
PR Template |
License |
README |
More than half checks (5/8)