v1.0.0

Summary

This version features a stable API, better inference performance, and user-friendly error reporting. Most importantly, tools have been added to make your model deployment in cloud environments hassle-free. Support for Apple Silicon was also added.

Links

Docker Image: zamafhe/concrete-ml:v1.0.0
pip: https://pypi.org/project/concrete-ml/1.0.0
Documentation: https://docs.zama.ai/concrete-ml

v1.0.0

Feature

• Add structured pruning to QNNs (70bff38)
• Add accumulator rounding (8ee9267)
• Add bitwidth and value range report per layer (dd37f4e)
• Extend deployment features (AWS and docker) (77e2d80)
• Add sentiment analysis deployment use-case (96c9158)
• Support ONNX operators Gather, Slice, Shape, ConstantOfShape (667e9ae)
• Include quant and dequant steps in QuantizedModule's forward method (55369ed)
• Add scikit-learn model serialization (ae7658b)
• Add cifar-10 8-bit model deployment (9177058)
• Support pandas and list inputs in predict and compile methods for NNs (6a5e619)
• Add example of model deployment to use-cases (be7bcb0)
• Support pandas, list and torch for trees and linear models (8156bc9)
• Simplify the API by removing n_bits for compile_brevitas_qat (d081212)

Fix

• Fix ci packaging (bdda1da)
• Fix deploy_to_aws for python 3.10 (7665809)
• Non-quantized NN constant folding bug (bdc04c4)
• Make the client-server API support Tweedie models (0de7398)
• QNN API improvements and pruning fix (33c4bf0)
• Set specific dependency versions (9729dc6)
• Flaky client server (3eb86c1)
• Fixing issues with pytest and macOS (a0c22fa)

Documentation

• Add tree experiments (e1c0ce0)
• Add chapter on optimization and simulation (5454620)
• Update simulation (d298459)
• Good quantization configurations for target accumulator bit-widths (ef6355f)
• Add rounding documentation (b7f56d5)
• Add an example that separates encryption, FHE execution and decryption (d4681fb)