---
markdown_generated_at: "2026-11-10"
title: "Cloud AI SDK"
url: "https://www.qualcomm.com/developer/cloud-ai-sdk"
---

# Cloud AI SDK

![](https://s7d1.scene7.com/is/image/dmqualcommprod/cloud-ai-sdk-hero-image-large)

[Get Started](https://docs.qualcomm.com/bundle/publicresource/topics/80-99100-1/cl-overview.html?product=1601111739980306)
[Download SDK](https://quic.github.io/cloud-ai-sdk-pages/latest/Getting-Started/Installation/Cloud-AI-SDK/Cloud-AI-SDK/)

[Docs](https://docs.qualcomm.com/bundle/publicresource/topics/80-99100-1/?product=1601111739980306)
[Software](https://www.qualcomm.com/developer/software/cloud-ai-sdk/software)
[Hardware](https://www.qualcomm.com/developer/software/cloud-ai-sdk/hardware)
[Support](https://www.qualcomm.com/developer/software/cloud-ai-sdk/support)

## What is Cloud AI SDK

Cloud AI SDKs enable developers to optimize trained deep learning models for high-performance inference on Qualcomm® Cloud AI 100 accelerators.

The Cloud AI SDKs provide workflows to optimize the models for best performance, provides runtime for execution and supports integration with ONNX Runtime and Triton Inference Server for deployment.

Product license agreement

### Featured Documents

[Documentation](https://docs.qualcomm.com/bundle/publicresource/topics/80-99100-1/cl-overview.html?product=1601111739980306)
[FAQs](https://www.qualcomm.com/developer/software/cloud-ai-sdk/support)

## Our trusted partners

### Cloud Service Providers

![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/cloud-service.png)

### Server Providers

![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/service-providers.png)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/aws-banner-background?fmt=webp-alpha&qlt=85&wid=1440&fit=fit,1)

Get started with Amazon EC2 DL2q instances powered by Qualcomm® AI 100 Standard accelerators.

[Visit AWS](https://aws.amazon.com/ec2/instance-types/dl2q/)

## Software architecture

![](https://s7d1.scene7.com/is/image/dmqualcommprod/cloud-ai-sdk-icon?$QC_Responsive$&fmt=png-alpha)

### Application (Apps) SDK

The Apps SDK is used to convert models and prepare runtime binaries for Cloud AI platforms. It contains model development tools, a sophisticated parallelizing graph compiler, performance and integration tools, and code samples. Apps SDK is supported on x86-64 Linux-based systems.

[Download SDK](https://quic.github.io/cloud-ai-sdk-pages/latest/Getting-Started/Installation/Cloud-AI-SDK/Cloud-AI-SDK/#apps-sdk)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/cloud-ai-sdk-icon?$QC_Responsive$&fmt=png-alpha)

### Platform SDK

The Platform SDK provides driver support for Cloud AI acclerators, APIs and tools for executing and debugging model binaries, and tools for card health, monitoring and telemetry. Platform SDK consists of a kernel driver, userspace runtime with APIs and language bindings, and card firmware. Platform SDK is supported on x86-64 and ARM64 hosts

[Download SDK](https://quic.github.io/cloud-ai-sdk-pages/latest/Getting-Started/Installation/Cloud-AI-SDK/Cloud-AI-SDK/#platform-sdk)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/cloud-ai-sdk-diagram?$QC_Responsive$&fmt=png-alpha)

## Use cases

Build your models to support any AI use case

- ![](https://s7d1.scene7.com/is/image/dmqualcommprod/EnhancedOSCapabilities1.png?$QC_Icon$&fmt=png-alpha) Generative AI/LLMs
- ![](https://s7d1.scene7.com/is/image/dmqualcommprod/NearFaceDetection1?$QC_Icon$&fmt=png-alpha) Natural Language Processing
- ![](https://s7d1.scene7.com/is/image/dmqualcommprod/EyeTracking1?$QC_Icon$&fmt=png-alpha) Object Detection
- ![](https://s7d1.scene7.com/is/image/dmqualcommprod/Images1?$QC_Icon$&fmt=png-alpha) Semantic Segmentation
- ![](https://s7d1.scene7.com/is/image/dmqualcommprod/trafficdetection1?$QC_Icon$&fmt=png-alpha) Traffic Detection
- ![](https://s7d1.scene7.com/is/image/dmqualcommprod/Electrification1?$QC_Icon$&fmt=png-alpha) Quality Control
- ![](https://s7d1.scene7.com/is/image/dmqualcommprod/licensing1?$QC_Icon$&fmt=png-alpha) Character Recognition
- ![](https://s7d1.scene7.com/is/image/dmqualcommprod/search1?$QC_Icon$&fmt=png-alpha) Search Engines

## Benefits

Flexible toolchain to meet the growing inference needs of cloud data centers.

### Running multiple complex AI models

![](https://s7d1.scene7.com/is/image/dmqualcommprod/brain-icon?$QC_Responsive$&fmt=png-alpha)

High performance Generative AI, Natural Language Processing, and Computer Vision models.

### Optimizing performance

![](https://s7d1.scene7.com/is/image/dmqualcommprod/performance-icon-2?$QC_Responsive$&fmt=png-alpha)

Optimizing performance of the models per application requirements (throughput, accuracy and latency) through various quantization techniques.

### Cross platforms apps development

![](https://s7d1.scene7.com/is/image/dmqualcommprod/cross-icon?$QC_Responsive$&fmt=png-alpha)

Development of inference applications through support
for multiple OS and Docker containers.

### Deployment at-scale

![](https://s7d1.scene7.com/is/image/dmqualcommprod/deployment-icon?$QC_Responsive$&fmt=png-alpha)

Deployment of inference applications at scale with support for Triton inference server.

### Power efficiency

![](https://s7d1.scene7.com/is/image/dmqualcommprod/power-icon-1?$QC_Responsive$&fmt=png-alpha)

Sets a higher bar for power efficient inference processing delivering the highest performance/watt.

## Resources

Accelerate your work with project cloning, AI models and tutorials.

##### Sample applications

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Build a natural language processing app in C++ with the BERT model](https://github.com/quic/cloud-ai-sdk/tree/1.12/samples/cpp/cpp_qpc_inference)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Build an image classification app in Python with the Vision Transformer model](https://github.com/quic/cloud-ai-sdk/tree/1.12/samples/python/vit_qaic)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Learn about profiling and benchmarking neural network models in Python](https://github.com/quic/cloud-ai-sdk/tree/1.12/samples/python/qaic_features)

##### AI model recipes

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Learn how to run the Stable Diffusion text-to-image generative AI model](https://github.com/quic/cloud-ai-sdk/tree/1.12/models/multimodal/text_to_image)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Convert and run language models from Hugging Face](https://github.com/quic/cloud-ai-sdk/tree/1.12/models/language_processing/encoder)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Convert and run computer vision models from TorchVision and Hugging Face](https://github.com/quic/cloud-ai-sdk/tree/1.12/models/vision/classification)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Convert and run the BERT model](https://github.com/quic/cloud-ai-sdk/blob/1.12/tutorials/NLP/Model-Onboarding-Beginner/getting-started-beginner.ipynb)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Tune the BERT model for best throughput and latency](https://github.com/quic/cloud-ai-sdk/blob/1.12/tutorials/NLP/Performance-Tuning-Beginner/Performance-tuning.ipynb)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/card-bg?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)
![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/software/cloud-ai-sdk/git-hub-eyebrow.png)
[Tune the ResNet50 model for best throughput and latency](https://github.com/quic/cloud-ai-sdk/blob/1.12/tutorials/Computer-Vision/Perfomance-Tuning-Beginner/Performance-tuning.ipynb)

##### Tutorials

- Stable Diffusion Notebook (8:07)
- Stable Diffusion Demo (1:09)
- CodeGen Notebook (6:54)

## Learn more

![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/cloud-ai-sdk/cloud-ai-left.png?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)

Cloud AI SDK platform in the cloud.

[Get started with AWS](https://aws.amazon.com/ec2/instance-types/dl2q/)
[Get started with Cirrascale](https://cirrascale.com/solutions-qualcomm-cloud-ai100.php)

![](https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets/images/developer/cloud-ai-sdk/cloud-ai-sdk-right.png?fmt=webp-alpha&qlt=85&wid=1800&fit=fit,1)

Cloud AI SDK on-premises

[Find an on-premise server](https://www.qualcomm.com/developer/software/cloud-ai-sdk/hardware)

## Latest news

OnQ Blog

[The power to transform retail with on-device generative AI](https://www.qualcomm.com/news/onq/2024/01/the-power-to-transform-retail-with-on-device-generative-ai)

Jan 12, 2024

[AI](https://www.qualcomm.com/news/onq?tags=AI) [Chipsets](https://www.qualcomm.com/news/onq?tags=Chipsets) [Internet of Things](https://www.qualcomm.com/news/onq?tags=Internet%20of%20Things)

OnQ Blog

[Frictionless Payments with IoT: The New Frontier for Retailers](https://www.qualcomm.com/news/onq/2023/02/frictionless-payments-with-iot-the-new-frontier-for-retailers)

Feb 16, 2023

[NRF](https://www.qualcomm.com/news/onq?tags=NRF) [IoT](https://www.qualcomm.com/news/onq?tags=IoT) [5G](https://www.qualcomm.com/news/onq?tags=5G)

OnQ Blog

[ICYMI: Qualcomm brought the future of retail to life at NRF 2022 [video]](https://www.qualcomm.com/news/onq/2022/04/icymi-qualcomm-brought-future-retail-life-nrf-2022)

Apr 11, 2022

[Internet of Things](https://www.qualcomm.com/news/onq?tags=Internet%20of%20Things) [Smart Cities](https://www.qualcomm.com/news/onq?tags=Smart%20Cities)

## Connect with our communities

[LinkedIn](https://www.linkedin.com/showcase/qualcomm-developer)
[See what's new](https://x.com/Qualcomm_Dev)
[YouTube](https://www.youtube.com/qualcommdev)
[GitHub](https://github.com/qualcomm)

![](https://s7d1.scene7.com/is/image/dmqualcommprod/discord-icon-1?$QC_Responsive$&fmt=png-alpha)
[Discord](https://discord.com/invite/qualcommdevelopernetwork)

[Visit the forum](https://mysupport.qualcomm.com/supportforums/s/)