Download Latest Version v4.9.2 - minor bugfixes and QoL source code.zip (11.4 MB)
Email in envelope

Get an email when there's a new version of SimpleTuner

Home / v4.9.0
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2026-08-30 5.0 kB
0
v4.9.0 - torch compile speedup, MegaCache import_export, NextLat, Explorative Modeling, block swap optimisations source code.tar.gz 2026-08-30 17.8 MB
0
v4.9.0 - torch compile speedup, MegaCache import_export, NextLat, Explorative Modeling, block swap optimisations source code.zip 2026-08-30 20.2 MB
0
Totals: 3 Items   38.0 MB 0

Breaking Change

  • Diffusers' group offload is removed in PR 3150
  • Torch inductor backend switched from python to c++ wrapper
  • MiniMax Music 3 training objectives changed; don't upgrade mid-run

Features

  • Uses torch inductor's C++ wrapper by default now for a large performance improvement for LTX 2.5 torch compiled training
  • Load and export torch Mega-Cache from/to huggingface hub or local disk via new --dynamo.. options
  • Built-in RVC trainer for music model dataset expansion, configurable inside dataloader
  • NextLatent (NextLat: https://arxiv.org/abs/2511.05963) trains a model to "form compact world models with coherent belief states", regularising the hidden states so the transition through the model is more smooth

  • Explorative Modeling (XM: https://explorative-modeling.github.io) improves output fidelity by training on only the "best" out of several possible loss candidates on each step. Trades more training-time compute for better results during inference.

  • Better MiniMax Music 3 training objectives

  • continuation mode trains the model to continue a generation from a given full starting prefix, up to a certain max length

  • random crop mode without full prefixing/continuation now anchors positions better

  • RamTorch now shares quantised weights across multiple GPU processes, reducing system VRAM consumption

Bugfixes

  • MiniMax H3 single file checkpoint loader / dataset (torchcodec compatibility) fixes
  • Generated checkpoint README/model card refined and includes MiniMax LM training mode info now
  • Musubi block swap is optimised a little by allowing it to completely replace streamed weights instead of moving them back to GPU
  • Musubi block swap and gradient checkpointing now work together correctly, not increasing VRAM more than required
  • torch compile now enables correctly (eg. regional or full dynamo compile modes)
  • SDNQ with torch compile now enabled and working fully for all configurations
  • torch compile reduce-overhead mode now works with activation checkpointing
  • LTX 2.5 graph breaks for torch compile are removed, incl when using Flash Attention 2

What's Changed

Full Changelog: https://github.com/bghira/SimpleTuner/compare/v4.8.0...v4.9.0

Source: README.md, updated 2026-08-30