vLLM Ships Day-0 Support for Step-5 Preview with Sparse Attention and MoE

vLLM announced day-0 support for StepFun's Step-5 Preview, a 604B-parameter multimodal MoE with 1M context, covering sparse attention, MTP, vision, and day-0 RL training recipes across Blackwell and Hopper, reducing sparse prefill latency by 2.2%.

2026-10-15 ~ 2026-10-15 · 4 related posts

• vLLM announces Day-0 support for Step 5 Preview across Blackwell and Hopper — vllm_project · 2026-10-15
• vLLM details Step 5 Preview's region-based sparse attention: score summaries, then attend — vllm_project · 2026-10-15
• vLLM ships Day-0 support for Step 5 Preview, cuts sparse prefill latency 2.2% on B300 — vllm_project · 2026-10-15
• vLLM Ships Day-0 Support for Step-5 Preview: 604B MoE with 1M Context and RL Recipes — vllm_project · 2026-10-15