Shameless plug to my own inference engine: https://github.com/computerex/dlgo

- Inference for a bunch of open weights architectures

- Diffusion image generation fir Z ai turbo

- Vision input into LLM for inference

- Vulkan/fast CPU, optimized kernels

- Playground for testing

- Last but not least, system one fast inference mode with same API semantics as Jev

Decision models work by using a backbone model like qwen 3.5 9b, along with a special linear head that provides the readout for the forward pass.