v1.3.0
mizorewww/laya-mlxv1.3.0May 5, 2026by p-e-w
Upgrading?
AI Summary
This release introduces support for Qwen3.5 and Gemma 4 models, alongside performance optimizations like reduced VRAM usage and improved reproducibility. It also adds an integrated benchmarking system and fixes various multi-GPU reporting and startup speed issues.
Key Highlights
- Support for Qwen3.5 and Gemma 4 models
- Reduced peak VRAM usage
- Integrated benchmarking system
- Reproducible runs
- Improved startup speed for help flags
New Features
- Reproducible runs
- Reduced peak VRAM usage
- Support for Qwen3.5 models
- Support for Gemma 4 models
- Integrated benchmarking system
- Configurable response prefix logic
- Model card generation for local models
- Improved automatic response prefix determination
- VRAM usage reporting fixes for multi-GPU setups
- Fixed division-by-zero error in evaluator
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
Related Repositories
public-apis/public-apis★ 491,363
A collective list of free APIs
NousResearch/hermes-agent★ 256,187
The agent that grows with you
yt-dlp/yt-dlp★ 200,406
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,639
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,712
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.