rknn-llm
RKLLM facilitates AI model deployment on Rockchip platforms like RK3588 and RK3576, supporting various models including LLAMA and ChatGLM3-6B. With tools like RKLLM-Toolkit and Runtime, it maximizes NPU performance. Version 1.1 offers new model support and optimized processing, noted for its quantization accuracy, though not backwards compatible. Compatible with Python 3.8 and 3.10, it suits diverse environments.