Skip to content

Latest commit

 

History

History
74 lines (56 loc) · 6.94 KB

README.md

File metadata and controls

74 lines (56 loc) · 6.94 KB
Raw

Cloud AI 100

| User Guide | Download SDK | Blog |

Qualcomm Cloud AI SDK - Developer Resources

Latest News 🔥

About

Qualcomm Cloud AI 100 provides a unique blend of high computational performance, low latency and low power utilization for deep learning inference and is well suited for a broad range of applications based on computer vision, natural language processing, and Generative AI including LLMs. It was purpose-built for high performance, low-power AI processing in the cloud – public and private (for Enterprise AI applications).

This repository provides developers with 3 key resources

  • Models - Recipes for CV, NLP, multimodal models to run on Cloud AI platforms performantly.
    For LLMs, see efficient-transformers
  • Tutorials - Tutorials cover model onboarding, performance tuning, and profiling aspects of inferencing across CV/NLP on Cloud AI platforms
  • Samples - Sample code illustrating usage of APIs - Python and C++ for inference on Cloud AI platforms

Supported Models

Generative AI - Large Language Models (LLMs)

Generative AI - Text-to-Image Models

  • Stable Diffusion (stabilityai/stable-diffusion-xl-base-1.0, stabilityai/stable-diffusion-2-1, runwayml/stable-diffusion-v1-5, etc.)
  • DeciDiffusion (Deci/DeciDiffusion-v2-0, Deci/DeciDiffusion-v1-0, etc.)

NLP - Encoder-only Transformer Models

  • 80+ models including all varieties of bert models, sentence-transformer embedding models, etc.

Computer Vision (CV) Models

  • ViT (vit_b_16, vit_b_32, vit-base-patch16-224)
  • YOLO (yolov5s, yolov5m, yolov5l, yolov5x, yolov7-e6e)
  • ResNet (resnet18, resnet34, resnet50, resnet101, resnet152)
  • ResNeXt (resnext101_32x8d, resnext101_64x4d, resnext50_32x4d)
  • Wide ResNet (wide_resnet101_2, wide_resnet50_2)
  • DenseNet (densenet121, densenet161, densenet169, densenet201)
  • MNASNet (mnasnet0_5, mnasnet0_75, mnasnet1_0, mnasnet1_3)
  • MobileNet (mobilenet_v2, mobilenet_v3_large, mobilenet_v3_small)
  • EfficientNet (efficientnet_v2_l, efficientnet_v2_m, efficientnet_v2_s, efficientnet_b0, efficientnet_b7, etc.)
  • ShuffleNet (shufflenet_v2_x0_5, shufflenet_v2_x1_0, shufflenet_v2_x1_5, shufflenet_v2_x2_0)
  • SqueezeNet (squeezenet1_0, squeezenet1_1)

Support

Use GitHub Issues to request for model support, raise questions or to provide feedback.

Disclaimer

While this repository may provide documentation on how to run models on Qualcomm Cloud AI platforms, this repository does NOT contain any of these models. All models referenced in this documentation are independently provided by third parties at unaffiliated websites. Please be sure to review any third-party license terms at these websites; no license to any model is provided in this repository. This repository of documentation provides no warranty or assurances for any model so please also be sure to review all model cards, model descriptions, model limitations / intended uses, training data, biases, risks, and any other warnings given by the third party model providers. While this repository may provide documentation on how to run models on Qualcomm Cloud AI platforms, this repository does NOT contain any of these models. All models referenced in this documentation are independently provided by third parties at unaffiliated websites. Please be sure to review any third-party license terms at these websites; no license to any model is provided in this repository. This repository of documentation provides no warranty or assurances for any model so please also be sure to review all model cards, model descriptions, model limitations / intended uses, training data, biases, risks, and any other warnings given by the third party model providers.

License

The documentation made available in this repository is licensed under the BSD 3-clause-Clear “New” or “Revised” License. Check out the LICENSE for more details.