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

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
https://intel.github.io/neural-compressor/

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

Last synced: 2 months ago
JSON representation

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

• Host: GitHub
• URL: https://intel.github.io/neural-compressor/
• Owner: intel
• License: apache-2.0
• Created: 2020-07-21T23:49:56.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2025-12-05T12:39:39.000Z (2 months ago)
• Last Synced: 2025-12-07T04:13:05.646Z (2 months ago)
• Topics: auto-tuning, awq, fp4, gptq, int4, int8, knowledge-distillation, large-language-models, low-precision, mxformat, post-training-quantization, pruning, quantization, quantization-aware-training, smoothquant, sparsegpt, sparsity
• Language: Python
• Homepage: https://intel.github.io/neural-compressor/
• Size: 436 MB
• Stars: 2,542
• Watchers: 30
• Forks: 283
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Security: SECURITY.md

Awesome Lists containing this project

• awesome-python - intel.github.io/neural-compressor