What’s New

Neuron 1.14.0 (05/28/2021)

This release (Neuron 1.14.0) introduces first release of Neuron PyTorch 1.8.1, tutorials update, performance enhancements and memory optimizations for Neuron PyTorch, Neuron TensorFlow and Neuron MXNet.

  • Neuron PyTorch - First release of Neuron PyTorch 1.8.1.

  • Neuron PyTorch - Convolution operator support has been extended to include ConvTranspose2d variants.

  • Neuron PyTorch - Updated tutorials to use Hugging Face Transformers 4.6.0.

  • Neuron PyTorch - Additional performance enhancements, memory optimizations, and bug fixes. see PyTorch Neuron release notes.

  • Neuron Compiler - New feature - Uncompressed NEFF format for faster loading models prior inference. Enable it by –enable-fast-loading-neuron-binaries. Some cases of large models may be detrimentally impacted as it will not be compressed but many cases will benefit.

  • Neuron Compiler - Additional performance enhancements, memory optimizations, and bug fixes, see Neuron Compiler Release Notes.

  • Neuron TensorFlow - Performance enhancements, memory optimizations, and bug fixes. see Tensorflow-Neuron Release Notes.

  • Neuron MXNet - Enhancements and minor bug fixes (MXNet 1.8), see Neuron Apache MXNet (Incubating) Release Notes.

  • Neuron Runtime - Performance enhancements, memory optimizations, and bug fixes. Neuron Runtime Release Notes.

  • Neuron Tools - Minor bug fixes and enhancements.

  • Software Deprecation

    • End of support for Neuron Conda packages in Deep Learning AMI, users should use pip upgrade commands to upgrade to latest Neuron version in DLAMI, see blog.

    • End of support for Ubuntu 16, see documentation.