This document is relevant for: Inf1, Inf2, Trn1, Trn2, Trn3

AWS Neuron SDK 2.27.0: Neuron Compiler release notes

Date of release: December 19, 2025

• Go back to the AWS Neuron 2.27.0 release notes home

• Review older release notes in the Previous Neuron Releases section.

Changes and improvements

• Error code docs New error code documentation has been added to help developers better understand and troubleshoot issues encountered during model compilation. Check them out here: Neuron Compiler Error Codes

• Compiler accuracy flag defaults updated: Two Neuron Compiler (neuronxcc) flags now have different default behaviors to improve accuracy. The --auto-cast flag now defaults to none (previously matmul), and --enable-mixed-precision-accumulation is now enabled by default. These changes optimize accuracy but may impact performance for FP32 models and models using smaller bitwidth dtypes. To restore previous behavior, explicitly set --auto-cast=matmul and use the new --disable-mixed-precision-accumulation flag.

• Python 3.9 no longer supported: The Neuron Compiler requires Python 3.10 or higher. Users currently on Python 3.9 must upgrade to continue using the Neuron Compiler with Python bindings.

This document is relevant for: Inf1, Inf2, Trn1, Trn2, Trn3