Skip to main content

​
Install / pip

Common on networks with TLS inspection — including Qualcomm Developer Cloud (QDC). Pre-download the SDK and point pip at the local file. See the full PowerShell snippet in Python install.
The .exe is not yet code-signed. Click More info → Run anyway in the SmartScreen dialog.

​
CLI

The installer doesn’t add itself to PATH. Run:
Set-Alias geniex (where.exe geniex)
Qualcomm AI Engine Direct is NPU-only. Use --compute npu (or omit the flag — npu is the default for qairt). To run on CPU/GPU, switch to a GGUF model on the llama.cpp runtime.

​
Server

The server doesn’t auto-download. Pull the model first:
geniex pull ai-hub-models/Qwen3-4B-Instruct-2507
Then restart geniex serve.
The --privileged flag is required for NPU access. Make sure your docker run includes it, plus the volume mounts for /usr/lib. See CLI install (Docker).

​
Linux

Two separate things have to be right:
  1. Registry login. Docker Hub (docker.io/qualcomm/geniex) is public and needs no login. For the Qualcomm Container Registry, log in first:
    bash
    # Qualcomm Container Registry:
docker login docker-registry.qualcomm.com -u '$app' -p GB2S6KXMJXTPV8VHNFNS7Q6LVH75LOOBTLT8D723WUX6PSFZMTX95GIQG4EFWH5C021ONZ5763VI9IDHU96Q7VAZJ2830CLX3NPI6STQOJWRYXLLA2ZYTL1S
    You should see Login Succeeded.
  2. Docker group membership. If docker pull returns permission denied while trying to connect to the docker API at unix:///var/run/docker.sock, your user isn’t in the docker group:
    bash
    sudo usermod -aG docker $USER
newgrp docker        # apply the new group in the current shell
    Then retry the pull.
On a fresh Ubuntu 24.04 ARM64 host (e.g. IQ9075 EVK), install.sh — and, for Docker, the pre-flight check.sh / container entrypoint.sh — check for libraries like libCB.so.1, libOpenCL_adreno.so.1, libcdsprpc.so.1.0.0, libgsl.so.1, libllvm-*.so.1, libpropertyvault.so.0.0.0, libdmabufheap.so.0.0.0, plus Debian’s libatomic1 / libglib2.0-0. Install them on the host in two steps — if you’re inside the geniex container, exit first.1. Standard APT packagesAddresses the libatomic1 and libglib2.0-0 requirements reported by the geniex installer, and provides a generic OpenCL ICD loader:
bash
sudo apt update
sudo apt install -y \
  libatomic1 \
  libglib2.0-0 \
  ocl-icd-libopencl1
ocl-icd-libopencl1 is replaced by qcom-adreno1 in the next step.
2. Qualcomm driver packages (via ubuntu-qcom-iot PPA)Provides the Qualcomm-proprietary libraries required by geniex:
Missing libraryProvided by
libOpenCL_adreno.so.1, libCB.so.1, libadreno_utils.so.1, libgsl.so.1, libllvm-*.so.1qcom-adreno1
libdmabufheap.so.0.0.0qcom-libdmabufheap (auto-dep of qcom-adreno1)
libpropertyvault.so.0.0.0qcom-property-vault (auto-dep of qcom-adreno1)
libcdsprpc.so.1.0.0qcom-fastrpc1
bash
sudo apt-get install -y qcom-adreno1 qcom-fastrpc1
The PPA (ppa:ubuntu-qcom-iot/qcom-ppa) is pre-configured on the IQ9075 EVK Ubuntu image. qcom-adreno1 automatically pulls in qcom-libdmabufheap and qcom-property-vault.After this, re-run install.sh (bare metal) or restart the container to confirm; the “Linking host NPU libraries” step should succeed. If libcdsprpc.so / libadsprpc.so symlinks are still missing on bare metal, re-run install.sh to recreate them.
The container can’t reach the NPU. Make sure your docker run includes --privileged and the /usr/lib mount, and that the host’s Qualcomm driver packages (qcom-adreno1, qcom-fastrpc1) are installed — see the missing-libraries entry above.

​
Android

The demo (or your code) is passing the raw user text into generateStreamFlow instead of the chat-templated prompt. Qualcomm AI Engine Direct pipelines treat their input as already-templated — pass applyChatTemplate().formattedText, not the raw user message.
Android needs an explicit chipset for Qualcomm AI Hub pulls — auto-detect only runs on Windows on Snapdragon. Set ModelPullInput.chipset to "SM8750" (Snapdragon 8 Elite) or "SM8850" (Snapdragon 8 Elite Gen 5). See Android API reference → ModelPullInput.
The model id returned by Qualcomm AI Hub must match an entry in the Qualcomm AI Engine Direct runtime’s registry (qwen3_4b_instruct_2507, qwen2_5_vl_7b_instruct, etc.). To add a new Qualcomm AI Hub Model, register it on the C++ side first — see third-party/geniex-qairt/models/{llm,vlm}_model_registry.h.
Qualcomm AI Hub Models are compiled with fixed KV cache and context length. Leave both nGpuLayers and nCtx at their defaults; tune max_tokens and enable_thinking instead.

​
Still stuck?

GitHub Issues

File a bug, request a feature, or browse open issues.

Slack

Developer collaboration.