MODEL REFERENCE / stepfun-ai

stepfun-ai/Step-5-Preview

Multimodal MoE with hybrid sparse/sliding-window attention, a 1M-token context window, and MTP.

vLLMSGLangmoe604B1,048,576 ctxvLLM +multimodal

02 / Configure

Configure serving

Choose engine, hardware and deployment options. The command updates as you go.

03 / Understand

Model notes and examples