Starstruk Logo MarkStarstruk

v1.3.0

jgraph/drawiov1.3.0May 5, 2026by p-e-w

AI Summary

This release focuses on performance optimizations, new model support, and stability improvements. It introduces support for Qwen3.5 and Gemma 4 models, reduces VRAM usage, and adds a benchmarking system. Several bug fixes related to multi-GPU setups and evaluation logic were also implemented.

Key Highlights

  • Added support for Qwen3.5 and Gemma 4 models
  • Reduced peak VRAM usage and fixed VRAM reporting for multi-GPU setups
  • Implemented an integrated benchmarking system and improved reproducible runs
  • Fixed a division-by-zero error in the evaluator
  • Improved automatic response prefix determination and startup speed

New Features

  • Reproducible runs
  • Qwen3.5 and Gemma 4 model support
  • Model card generation for local models
  • Integrated benchmarking system
  • Configurable response prefix logic

Full Release Notes

## Changes

* @Vinay-Umrethe (who had previously contributed under the username @Vinayyyy7) implemented reproducible runs in https://github.com/p-e-w/heretic/pull/191. @p-e-w revised and improved that implementation in https://github.com/p-e-w/heretic/pull/303.
* @magiccodingman reduced peak VRAM usage in https://github.com/p-e-w/heretic/pull/239. @olekssy fixed a bug in that implementation in https://github.com/p-e-w/heretic/pull/301.
* @farolone added support for Qwen3.5 models in https://github.com/p-e-w/heretic/pull/187
* @MoonRide303 added support for Gemma 4 models in https://github.com/p-e-w/heretic/pull/287
* @erm14254 made sure all abliterable components across layers are displayed in https://github.com/p-e-w/heretic/pull/215
* @cpagac fixed VRAM usage reporting for multi-GPU setups in https://github.com/p-e-w/heretic/pull/169
* @cpagac fixed a division-by-zero error in the evaluator in https://github.com/p-e-w/heretic/pull/225
* @spikymoth improved automatic response prefix determination with a two-step process in https://github.com/p-e-w/heretic/pull/194
* @spikymoth added model card generation for local models with an existing README in https://github.com/p-e-w/heretic/pull/157
* @Diplo2by improved startup speed when Heretic is run with `-h`/`--help` in https://github.com/p-e-w/heretic/pull/293
* @AWuhrmann fixed the example value for the `max_memory` setting in https://github.com/p-e-w/heretic/pull/284
* @p-e-w added an integrated benchmarking system, made the response prefix logic configurable, implemented multiple infrastructure improvements, and fixed various minor issues

## New Contributors

* @cpagac made their first contribution in https://github.com/p-e-w/heretic/pull/169
* @farolone made their first contribution in https://github.com/p-e-w/heretic/pull/187
* @erm14254 made their first contribution in https://github.com/p-e-w/heretic/pull/215
* @AWuhrmann made their first contribution in https://github.com/p-e-w/heretic/pull/284
* @MoonRide303 made their first contribution in https://github.com/p-e-w/heretic/pull/287
* @Diplo2by made their first contribution in https://github.com/p-e-w/heretic/pull/293
* @magiccodingman made their first contribution in https://github.com/p-e-w/heretic/pull/239
* @olekssy made their first contribution in https://github.com/p-e-w/heretic/pull/301

**Full Changelog**: https://github.com/p-e-w/heretic/compare/v1.2.0...v1.3.0