Intel® Low Precision Optimization Tool v1.5.1 release is featured by:

• Gradient-sensitivity pruning for CNN model
• Static quantization support for ONNX NLP model
• Dynamic seq length support in NLP dataloader
• Enrich quantization statistics

Validated Configurations:

• Python 3.6 & 3.7 & 3.8 & 3.9
• Centos 8.3 & Ubuntu 18.04
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0, 2.4.0, 2.5.0 and 1.15.0 UP1 & UP2 & UP3
• PyTorch 1.5.0+cpu, 1.6.0+cpu, 1.8.0+cpu, ipex
• MxNet 1.6.0, 1.7.0
• ONNX Runtime 1.6.0, 1.7.0, 1.8.0

Distribution:

Contact:

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

Intel® Low Precision Optimization Tool v1.5 release is featured by:

• Add pattern-lock sparsity algorithm for NLP fine-tuning tasks
  • Up to 70% unstructured sparsity and 50% structured sparsity with <2% accuracy loss on 5 Bert finetuning tasks
• Add NLP head pruning algorithm for HuggingFace models
  • Performance speedup up to 3.0X within 1.5% accuracy loss on HuggingFace BERT SST-2
• Support model optimization pipeline
• Integrate SigOPT with multi-metrics optimization
  • Complementary as basic strategy to speed up the tuning
• Support TensorFlow 2.5, PyTorch 1.8, and ONNX Runtime 1.8

Validated Configurations:

• Python 3.6 & 3.7 & 3.8 & 3.9
• Centos 8.3 & Ubuntu 18.04
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0, 2.4.0, 2.5.0 and 1.15.0 UP1 & UP2 & UP3
• PyTorch 1.5.0+cpu, 1.6.0+cpu, 1.8.0+cpu, ipex
• MxNet 1.6.0, 1.7.0
• ONNX Runtime 1.6.0, 1.7.0, 1.8.0

Distribution:

Contact:

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

Intel® Low Precision Optimization Tool v1.4.1 release is featured by:

1. Support TensorFlow 2.5.0
2. Support PyTorch 1.8.0
3. Support TensorFlow Object Detection YOLO-V3 model

Validated Configurations:

• Python 3.6 & 3.7 & 3.8
• Centos 7 & Ubuntu 18.04
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0, 2.4.0, 2.5.0 and 1.15.0 UP1 & UP2
• PyTorch 1.5.0+cpu, 1.6.0+cpu, ipex
• MxNet 1.7.0
• ONNX Runtime 1.6.0, 1.7.0

Distribution:

Contact:

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

Intel® Low Precision Optimization Tool v1.4 release is featured by:

Quantization

1. PyTorch FX-based quantization support
2. TensorFlow & ONNX RT quantization enhancement

Pruning

1. Pruning/sparsity API refinement
2. Magnitude-based pruning on PyTorch

Model Zoo

1. INT8 key models updated (BERT on TensorFlow, DLRM on PyTorch, etc.)
2. 20+ HuggingFace model quantization

User Experience

1. More comprehensive logging message
2. UI enhancement with FP32 optimization, auto-mixed precision (BF16/FP32), and graph visualization
3. Online document: https://intel.github.io/lpot

Extended Capabilities

1. Model conversion from QAT to Intel Optimized TensorFlow model

Validated Configurations:

• Python 3.6 & 3.7 & 3.8
• Centos 7 & Ubuntu 18.04
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0, 2.4.0 and 1.15.0 UP1 & UP2
• PyTorch 1.5.0+cpu, 1.6.0+cpu, ipex
• MxNet 1.7.0
• ONNX Runtime 1.6.0, 1.7.0

Distribution:

Contact:

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

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

1. Improve graph optimization without explicit input/output setting

Validated Configurations:

• Python 3.6 & 3.7 & 3.8
• Centos 7 & Ubuntu 18.04
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0, 2.4.0 and 1.15.0 UP1 & UP2
• PyTorch 1.5.0+cpu, 1.6.0+cpu, ipex
• MxNet 1.7.0
• ONNX Runtime 1.6.0, 1.7.0

Distribution:

Contact:

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

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:

• Python 3.6 & 3.7 & 3.8
• Centos 7 & Ubuntu 18.04
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0, 2.4.0 and 1.15.0 UP1 & UP2
• PyTorch 1.5.0+cpu, 1.6.0+cpu, ipex
• MxNet 1.7.0
• ONNX Runtime 1.6.0, 1.7.0

Distribution:

Contact:

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

Intel® Low Precision Optimization Tool v1.2.1 release is featured by:

1. user-facing APIs backward compatibility with v1.1 and v1.0.
2. refined experimental user-facing APIs for better out-of-box experience.

Validated Configurations:

• Python 3.6 & 3.7 & 3.8
• Centos 7 & Ubuntu 18.04
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0, 2.4.0 and 1.15.0 UP1 & UP2
• PyTorch 1.5.0+cpu, 1.6.0+cpu, ipex
• MxNet 1.7.0
• ONNX Runtime 1.6.0

Distribution:

Contact:

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

Intel® Low Precision Optimization Tool v1.2 release is featured by:

• Broad TensorFlow model type support
• operator-wise quantization scheme for ONNX RT
• MSE driven tuning for metric-free use cases
• UX improvement, including UI web server preview support
• More key model supports

Validated Configurations:

• Python 3.6 & 3.7 & 3.8
• Centos 7 & Ubuntu 18.04
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0, 2.4.0 and 1.15.0 UP1 & UP2
• PyTorch 1.5.0+cpu, 1.6.0+cpu, ipex
• MxNet 1.7.0
• ONNX Runtime 1.6.0

Distribution:

Contact:

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

Intel® Low Precision Optimization Tool v1.1 release is featured by:

• New backends (PyTorch/IPEX, ONNX Runtime) backend preview support
• Add built-in industry dataset/metric and custom registration
• Preliminary input/output node auto-detection on TensorFlow models
• New INT8 quantization recipes: bias correction and label balance

Validated Configurations:

• Python 3.6 & 3.7
• Centos 7
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0 and 1.15.0 UP1 & UP2
• PyTorch 1.5.0+cpu
• MxNet 1.7.0
• ONNX Runtime 1.6.0

Distribution:

Contact:

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

Intel® Low Precision Optimization Tool v1.0 release is featured by:

• Refined user facing APIs for best OOB.
• Add TPE tuning strategies (Experimental).
• Pruning POC support on PyTorch
• TensorBoard POC support for tuning analysis.
• Built-in INT8/Dummy dataloader Support.
• Built-in Benchmarking support.
• Tuning history for strategy finetune.
• Support TF Keras and checkpoint model type as input.

Validated Configurations:

• Python 3.6 & 3.7
• Centos 7
• Intel TensorFlow 1.15.2, 2.1.0, 2.2.0, 2.3.0 and 1.15UP1
• PyTorch 1.5.0+cpu
• MxNet 1.7.0

Distribution:

Contact:

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