GitHub · Python
intel/neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
- Stars
- 2,730
- Forks
- 333
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: low-precision, pruning, sparsity, auto-tuning, knowledge-distillation, quantization, quantization-aware-training, post-training-quantization, smoothquant, large-language-models
Latest data point: Nov 20, 2026 · 2,730 stars · 333 forks