4 papers
Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling
Jiaqi Yang, Jiayi Li, Yihan Fu +5
Prefill-decode disaggregation (PD) and roofline-based operator placement are common strategies for partitioning Large Language Model (LLM) inference across heterogeneous systems, b…
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…
Step-DeepResearch Technical Report
Chen Hu, Haikuo Du, Heng Wang +64
As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands f…
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
StepFun, :, Bin Wang +195
Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hard…