Skip to content

Pinned Loading

  1. ax-samples ax-samples Public

    Samples code for world class Artificial Intelligence SoCs for computer vision applications.

    CMake 303 65

  2. awesome-docs awesome-docs Public

    As much as possible, facilitate users' assessment of the "One-Finger Zen" feature of the AX NPU, reduce the sunk cost, and encourage everyone to do something more valuable instead of getting stuck …

    JavaScript 5 10

  3. ax-llm ax-llm Public

    Explore LLM model deployment based on AXera's AI chips, It provides OpenAI‑compatible APIs and supports AX620E, AX650 and AX637 series chips.

    C++ 169 31

  4. ax-pipeline ax-pipeline Public

    The Pipeline example based on AX650N/AX8850 shows the software development skills of Image Processing, NPU, Codec, and Display modules, which is helpful for users to develop their own multimedia a…

    C++ 24 17

  5. QAT.Ultralytics QAT.Ultralytics Public

    This project is built upon the official Ultralytics repository, delivering QAT quantization solutions for various Axera chip platforms. It supports YOLOv8, YOLO11 and YOLO26 models with INT quantiz…

    Python 13 3

  6. Magnetar Magnetar Public

    Pulsar2 Agent, Build a 10‑stage automated pipeline powered by AI Agent. Convert floating‑point models into out‑of‑the‑box full AX‑chip delivery packages with a single natural‑language instruction t…

    Python 22 8

Repositories

Showing 10 of 144 repositories
  • laya-axera Public Forked from mizorewww/laya-mlx

    Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

    AXERA-TECH/laya-axera's past year of commit activity
    JavaScript 1 Apache-2.0 461 0 0 Updated Sep 24, 2026
  • QAT.PaddleOCR Public

    This project is based on Baidu's PaddleOCR and AXERA's self-developed Tongyuan mixed-precision NPU, implementing quantization-aware training (QAT) for PaddleOCR models and efficient deployment on the NPU side.

    AXERA-TECH/QAT.PaddleOCR's past year of commit activity
    Python 0 Apache-2.0 0 0 0 Updated Sep 22, 2026
  • laya.axera Public

    Laya typed-decision models for AX8850/NPU3: ONNX export, task-aware calibration, Pulsar2 build, and board validation.

    AXERA-TECH/laya.axera's past year of commit activity
    Python 1 Apache-2.0 0 0 0 Updated Sep 22, 2026
  • ax-llm Public

    Explore LLM model deployment based on AXera's AI chips, It provides OpenAI‑compatible APIs and supports AX620E, AX650 and AX637 series chips.

    AXERA-TECH/ax-llm's past year of commit activity
    C++ 169 BSD-3-Clause 31 13 2 Updated Sep 22, 2026
  • AXERA-TECH/Multimodal_RAG-AX650N's past year of commit activity
    Python 2 AGPL-3.0 0 0 0 Updated Sep 19, 2026
  • DEIMv2.axera Public

    [DEIMv2] Real Time Object Detection Meets DINOv3 Demo on Axera NPU

    AXERA-TECH/DEIMv2.axera's past year of commit activity
    Python 2 BSD-3-Clause 1 0 0 Updated Sep 19, 2026
  • Qwen3-VL.AXERA Public

    Demo for Qwen3 VL Series Models

    AXERA-TECH/Qwen3-VL.AXERA's past year of commit activity
    Python 8 2 0 0 Updated Sep 18, 2026
  • AXERA-TECH/QAT.Ultralytics.YOLOv5's past year of commit activity
    Python 8 AGPL-3.0 4 0 0 Updated Sep 16, 2026
  • ABot-Recon-Axera Public

    基于 AXCL/AX650 边缘算力,运行 Abot-Recon 单目三维重建

    AXERA-TECH/ABot-Recon-Axera's past year of commit activity
    Python 4 Apache-2.0 1 0 0 Updated Sep 16, 2026
  • ax-video-sdk Public

    基于 AXERA 的 SDK 实现,简单易懂的C++现代编解码库,支持axcl/ax650/ax620e(ax630c/ax620q/ax620qp),支持jpeg编解码,支持264/265编解码

    AXERA-TECH/ax-video-sdk's past year of commit activity
    C++ 8 6 1 0 Updated Sep 15, 2026