MyGit

v1.3

intel/neural-compressor

版本发布时间: 2021-04-16 22:58:24

intel/neural-compressor最新发布版本:v2.6(2024-06-14 21:55:11)

Intel® Low Precision Optimization Tool v1.3 release is featured by:

  1. FP32 optimization & auto-mixed precision (BF16/FP32) for TensorFlow
  2. Dynamic quantization support for PyTorch
  3. ONNX Runtime v1.7 support
  4. Configurable benchmarking support (multi-instances, warmup, etc.)
  5. Multiple batch size calibration & mAP metrics for object detection models
  6. Experimental user facing APIs for better usability
  7. Various HuggingFace models support

Validated Configurations:

Distribution:

  Channel Links Install Command
Source Github https://github.com/intel/lpot.git $ git clone https://github.com/intel/lpot.git
Binary Pip https://pypi.org/project/lpot $ pip install lpot
Binary Conda https://anaconda.org/intel/lpot $ conda install lpot -c conda-forge -c intel

Contact:

Please feel free to contact lpot.maintainers@intel.com, if you get any questions.

相关地址:原始地址 下载(tar) 下载(zip)

查看:2021-04-16发行的版本