Embeddable physically based renderer
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
A flexible, high-performance carrier for machine learning models（『飞桨』服务化部署框架）
LLM inference in C/C++