RCEpic
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
- Owner
- intel (organization)
- Stars
- Stars: 2,729
- Forks
- Forks: 332
- Language
- Python
- License
- Apache-2.0
- Created
- 2020
- Topics
- low-precisionpruningsparsityauto-tuningknowledge-distillationquantizationquantization-aware-trainingpost-training-quantizationsmoothquantlarge-language-models
- Tier
- RC (2,000 to 4,999 ★) What this tier means
More repos by intel
All 187 repos by intel- intel/intel-one-monoStars: 10,202Stable
- intel/ipex-llmStars: 8,845PythonStable
- intel/hyperscanStars: 5,513C++Stable
- intel/pcmStars: 3,353C++RC
- intel/haxmStars: 3,306CRC
- intel/acatStars: 3,231C#RC
Nearby in Python
All Python repos- elapouya/python-docx-templateStars: 2,729PythonRC
- allanzelener/YAD2KStars: 2,729PythonRC
- AmberSahdev/Open-InterfaceStars: 2,729PythonRC
- decompiler-explorer/decompiler-explorerStars: 2,726PythonRC