SGLang announces Day-0 support for StepFun's Step 5 Preview, a 600B-parameter sparse MoE model with 27B active per token and a 1M-token context window.
The post says Step 5 Preview is already served in production with hybrid attention, MTP decoding and cache-aware routing, and that Miles adds Day-0 RL training support.
Serving and training recipes are in its blog, and open weights are on Hugging Face and ModelScope.
The post names the inference and training setup, including hybrid attention and Day-0 RL support, showing how the open-weight model is served and trained.
SGLang brings Day-0 support for Step 5 Preview, @StepFun_ai’s flagship model for agentic work.
600B total, 27B active, 1M context, image input with
- Hybrid attention: recent window + selected older context, no full-history reads in every layer
- MTP decoding and cache-aware routing, already serving Step 5 Preview in production
- Miles adds Day-0 RL support for training on your own tasks
Serving and training recipes in the blog 👇
https://www.sglang.io/blog/step-5-preview-day0-support
Step 5 Preview is now open weights. BF16 and FP8 weights are live on Hugging Face and ModelScope, together with our technical blog. • Sparse MoE: 600B total, 27B active per token • 1M-token context window • Native text and vision input • Built for long-horizon agentic work: coding, software engineering, professional knowledge work and finance Frontier intelligence, open weights. Build what's next. Hugging Face: https://huggingface.co/stepfun-ai/Step-5-Preview ModelScope: https://modelscope.ai/models/stepfun-ai/Step-5-Preview GitHub: https://github.com/stepfun-ai/Step-5-Preview
Source: SGLang · x.comPublished
