Skip to content
@stepfun-ai

stepfun-ai

Pinned Loading

  1. Step-3.5-Flash Step-3.5-Flash Public

    Fast, Sharp & Reliable Agentic Intelligence

    C++ 1.2k 36

Repositories

Showing 10 of 27 repositories
  • Step-3.5-Flash Public

    Fast, Sharp & Reliable Agentic Intelligence

    stepfun-ai/Step-3.5-Flash’s past year of commit activity
    C++ 1,195 Apache-2.0 36 5 5 Updated Feb 11, 2026
  • GEBench Public
    stepfun-ai/GEBench’s past year of commit activity
    Python 40 Apache-2.0 0 0 0 Updated Feb 10, 2026
  • Step-Audio-EditX Public

    A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech

    stepfun-ai/Step-Audio-EditX’s past year of commit activity
    Python 870 Apache-2.0 58 30 2 Updated Feb 9, 2026
  • PaCoRe Public

    PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning

    stepfun-ai/PaCoRe’s past year of commit activity
    Python 317 10 0 0 Updated Feb 5, 2026
  • StepDeepResearch Public

    Step-DeepResearch

    stepfun-ai/StepDeepResearch’s past year of commit activity
    Python 499 Apache-2.0 20 3 0 Updated Feb 2, 2026
  • vllm Public Forked from vllm-project/vllm

    A high-throughput and memory-efficient inference and serving engine for LLMs

    stepfun-ai/vllm’s past year of commit activity
    Python 41 Apache-2.0 13,480 0 1 Updated Feb 2, 2026
  • Step-Audio Public
    stepfun-ai/Step-Audio’s past year of commit activity
    Python 4,614 Apache-2.0 373 65 3 Updated Jan 30, 2026
  • StepMesh Public
    stepfun-ai/StepMesh’s past year of commit activity
    C++ 343 Apache-2.0 36 10 1 Updated Jan 28, 2026
  • gelab-zero Public

    STEP-GUI: The top GUI agent solution in the galaxy. Developed by the StepFun-GELab team and powered by StepFun’s cutting-edge research capabilities.

    stepfun-ai/gelab-zero’s past year of commit activity
    Python 1,993 MIT 171 37 4 Updated Jan 23, 2026
  • Step3-VL-10B Public

    Step3-VL-10B: A compact yet frontier multimodal model achieving SOTA performance at the 10B scale, matching open-source models 10-20x its size.

    stepfun-ai/Step3-VL-10B’s past year of commit activity
    394 Apache-2.0 26 14 2 Updated Jan 21, 2026
View all repositories

Most used topics

Loading…