4Paradigm and RiseUnion open-source ModelSphere for heterogeneous LLM serving

4Paradigm and RiseUnion have open-sourced ModelSphere under Apache 2.0, a platform that manages compute, model serving and runtime tuning above engines like vLLM and SGLang.

It schedules Huawei Ascend, Iluvatar, Moore Threads and Hygon DCU resources through an EngineX inference layer. The companies claim about 285% higher peak throughput versus an internal baseline, a figure they have not had independently verified.