Skip to content
@qualcomm

Qualcomm Technologies, Inc.

At Qualcomm Technologies, Inc., we transform how the world connects, computes and communicates.
README.md

At Qualcomm Technologies, Inc., we transform how the world connects, computes and communicates. We are on a journey to embrace open source, its upstream contribution model and industry standards to make it easy for developers to innovate, build and scale.

Featured on-device AI projects

  • AI Model Efficiency Toolkit (AIMET): Advanced quantization and compression techniques to optimize trained neural networks for efficient inference
  • GenieX SDK: A high‑performance on-device inference framework that runs the latest multimodal models locally on NPU/GPU/CPU across common platforms
  • Qualcomm® AI Hub Models: A collection of deployment-ready ML models optimized for on-device performance and ready to run on Qualcomm devices

Explore our organizations and projects

Join our Discord community to directly engage with Qualcomm experts, connect with other developers working with Qualcomm technology, and stay updated on the latest developer-focused news and product demos: discord.com/invite/QualcommDeveloperNetwork

Read our Open Source Security Policy to learn how we handle vulnerability reporting, assessment, remediation, and disclosure across our open source projects.

Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. AIMET and AudioReach are products of Qualcomm Innovation Center, Inc.

Pinned Loading

  1. GenieX GenieX Public

    Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

    Rust 8.4k 1.1k

  2. aimet aimet Public

    AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

    Python 2.7k 467

  3. ai-hub-models ai-hub-models Public

    Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

    Python 1.2k 213

  4. ai-hub-apps ai-hub-apps Public

    The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

    Python 464 125

  5. eld eld Public

    Embedded Linker (eld)

    C++ 261 86

  6. fastrpc fastrpc Public

    FastRPC is Qualcomm's userspace library that facilitates efficient remote procedure calls between the CPU and DSP for high-performance computing.

    C 119 78

Repositories

Showing 10 of 162 repositories
  • GenieX Public

    Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

    qualcomm/GenieX's past year of commit activity
    Rust 8,425 BSD-3-Clause 1,068 44 27 Updated Oct 9, 2026
  • cpullvm-toolchain Public
    qualcomm/cpullvm-toolchain's past year of commit activity
    LLVM 22 36 7 32 Updated Oct 9, 2026
  • qemu Public Forked from qemu/qemu

    Official QEMU mirror. Please see http://wiki.qemu.org/Contribute/SubmitAPatch for how to submit changes to QEMU. Pull Requests are ignored. Please only use release tarballs from the QEMU website.

    qualcomm/qemu's past year of commit activity
    C 31 7,437 0 9 Updated Oct 9, 2026
  • eld Public

    Embedded Linker (eld)

    qualcomm/eld's past year of commit activity
    C++ 261 BSD-3-Clause 86 248 (13 issues need help) 101 Updated Oct 9, 2026
  • qimsdk Public
    qualcomm/qimsdk's past year of commit activity
    C 3 BSD-3-Clause-Clear 8 0 2 Updated Oct 9, 2026
  • camera-service Public

    Camera Service : It provides a camera service that loads the CamX libraries to interact with the camera hardware module. Additionally, it offers client APIs for communication with the service. Applications such as GStreamer-based apps can use these client APIs to access the camera feed and build end-user solutions.

    qualcomm/camera-service's past year of commit activity
    C++ 6 BSD-3-Clause-Clear 15 0 5 Updated Oct 9, 2026
  • efficient-transformers Public

    This library empowers users to seamlessly port pretrained models and checkpoints on the HuggingFace (HF) hub (developed using HF transformers library) into inference-ready formats that run efficiently on Qualcomm Cloud AIxx (AI100, AI200 and so on) accelerators.

    qualcomm/efficient-transformers's past year of commit activity
    Python 100 111 4 75 Updated Oct 9, 2026
  • qdte-lite Public

    Lightweight device tree editor for Qualcomm config-ELF containers

    qualcomm/qdte-lite's past year of commit activity
    Python 1 BSD-3-Clause-Clear 2 0 0 Updated Oct 9, 2026
  • llama.cpp Public Forked from ggml-org/llama.cpp

    LLM inference in C/C++

    qualcomm/llama.cpp's past year of commit activity
    C++ 15 MIT 24,722 0 0 Updated Oct 9, 2026
  • fastrpc Public

    FastRPC is Qualcomm's userspace library that facilitates efficient remote procedure calls between the CPU and DSP for high-performance computing.

    qualcomm/fastrpc's past year of commit activity
    C 119 78 23 17 Updated Oct 9, 2026
View all repositories