inclusionAI / AReno

What it does

• Plug-and-play. various post-training methods are easily accessible via the --algo flag or the same Trainer class from Python, no cluster or launcher to set up.
• Lightweight. one self-contained train/serve stack with CUDA, Ascend NPU, and Apple Silicon MLX backends.
• Agentic RL ready. run an agent function against AReno's local OpenAI-compatible proxy, return explicit trajectories, and train from tokens, logprobs, rewards, and loss masks derived by the trainer.
• Multimodal. use image, audio, and video content with compatible model processors through the same OpenAI-style message format in serving and agentic training.
• Native LoRA. train TP-aware adapters for Qwen3, Qwen3-MoE, and Bailing-MoE V3, save standard PEFT artifacts, and reload them for training or serving.