intel/
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
by Intel® Corporation Python Apache-2.0 licence 332 forks Created Jul 2020 View on GitHub
- Stars
- 2,730
- 2% of intel's stars
- Rank
- #24,867
- of 847,083 repos, top 3%
- In Python
- #4,483
- of 172,210 repos, top 3%
Among 847,083 repos
2.5k–4k stars: 10,603 repos, including neural-compressor
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #24,855
- Next milestone
- +4,503 stars to reach the top 1%
- Popular
- One of 66,319 repos with 1k+ stars
- Yearly average
- 433 stars a year since Jul 2020