mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-10-02 03:14:52 +08:00
Ubuntu 26.04 is here and very soon, NVIDIA PyTorch containers will ship with Python 3.14 requiring us to enable untested support to unblock them <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * DFlash offline speculative decoding training * MXFP4→NVFP4 weight conversion support * Shared hidden-state dump utilities * Updated DeepSeek PTQ calibration defaults * **Chores** * Added Python 3.14 support; updated Python requirement to <3.15 * **Documentation** * Updated installation documentation for Python version compatibility <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>