Native Swift implementation of OpenJev: Jev-compatible typed decisions (yes/no, choice, score) read from model probabilities, on Apple silicon Macs and in iPhone apps. Apache-2.0.
FastMCP fleet MCP server for diffusion LMs (dLLM). DiffusionGemma on Goliath RTX 4090 — batch inference, HLE-shaped reasoning, ~200–400 tok/s. Doc phase; llama-diffusion-cli sidecar next. Complements local-llm-mcp.
Decision Model - Calibrated DiffusionGemma template evaluation cli, mcp, web app for fast, confident zero-shot decision making.
DiffusionGemma node pack for ComfyUI, built on MCP backbone for fully-agentic consumption — discrete diffusion text generation with per-step canvas snapshots, commit heatmaps, and structured trace data. Watch meaning crystallize out of noise.
Jev-style typed decision engine on a diffusion LM (DiffusionGemma + MLX): one-pass slot reads, calibration, domain LoRA. Not affiliated with TypeSafe AI.
Any LLM can serve as SystemOne decision model on your Personal Computer. And support for LLaDA-MoE/DiffusionGemma.
llama.cpp fork with experimental DiffusionGemma full-GPU and CUDA fusion support
Docker-Compose template to self-host Google DiffusionGemma 26B on an NVIDIA GPU host via llama.cpp
Matrix-style logit conditioning for DiffusionGemma's llama.cpp denoiser
Native WinUI 3 control panel for running local llama.cpp and DiffusionGemma backends with model management, Hugging Face downloads, runtime tuning, logs, and resource monitoring.
Local DiffusionGemma coding agent for Windows, WSL2, and 16 GB NVIDIA GPUs
Open-source Jev harness for TypeSafe, OpenJev, LocalJev, Ollama, vLLM, LM Studio, llama.cpp. Typed decisions, calibration, verification, abstention, CI gates.
To associate your repository with the diffusiongemma topic, visit your repo's landing page and select "manage topics."