mizorewww/laya-mlx

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A native MLX runtime for Laya typed decision models on Apple Silicon. It performs local inference without text generation, a PyTorch runtime, or a cloud API.

How it helps ATF

Harness can compare this runtime when considering local typed decisions as a component separate from agent execution.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

• mizorewww/laya-coreml
  A port of Laya typed decision models to Apple Core ML and the Neural Engine, running on device without generating tokens, published with speed and energy benchmarks and a Snake demo.
• jaredpalmer/kev
  Small Qwen3.5-based decision models with pretrained weights, training code, and evaluation data. The API supports yes/no, multiple-choice, and rating questions and matches TypeSafe System One.
• Taichu-AI/ZDTaichu5.0-9B
  A multimodal model supporting text, images, and video for visual understanding, spatial reasoning, agent tool use, and embodied-AI research. It combines a Qwen3.5-9B language backbone with a C-RADIOv4-H vision encoder.
• whitecircle/halo
  A training framework for language and multimodal models supporting pretraining, supervised fine-tuning, preference optimization, and asynchronous multi-turn reinforcement learning. It runs Hugging Face models on one GPU or across nodes.
• NVIDIA/Model-Optimizer
  A model optimization library with quantization, pruning, distillation and speculative decoding. It exports optimized checkpoints for downstream inference frameworks.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.