OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Infrastructure & Serving

Cloud AI SDK

Cloud AI SDK is a repository of model recipes, tutorials, sample applications and utilities for deep-learning inference on Qualcomm Cloud AI accelerator platforms. It includes resources for computer vision, object detection, NLP and generative-AI workloads, with examples of Triton model serving, vLLM-based language-model serving and LLM benchmarking.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cloud AI SDK — OpenViST project profile in AI Infrastructure & Serving.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when developing or evaluating inference workflows specifically for Qualcomm Cloud AI platforms, and consult the relevant model recipe or user guide for the required platform setup.

Who it is for

  • Developers building inference workflows for Qualcomm Cloud AI accelerator hardware.
  • Teams onboarding, tuning or profiling computer-vision and NLP models on those platforms.

Documented uses

  • Adapt and run documented model recipes for computer-vision and NLP inference.
  • Use Python or C++ examples to understand inference API usage.
  • Serve an object-detection model with Triton or a language model with the documented vLLM container workflow.
  • Explore benchmarking resources for LLM inference workloads.
Before you choose

Requirements & limits

The GitHub repository is public. Its public visibility does not establish license terms.

  • The examples target Qualcomm Cloud AI accelerator platforms and are not presented as hardware-independent workflows.
  • The repository combines distinct resources: model recipes, tutorials, Python and C++ samples, and utilities such as QAic Bench.
  • The documented YOLOv8 path uses Docker Compose and Triton; the LLM serving example uses a vLLM container with accelerator-device access.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run the documented YOLOv8 Triton example

Build the example container, prepare its Triton model repository, start the server and request object-detection inference.

Before you start

  • Qualcomm Cloud AI accelerator hardware and its required software environment
  • Docker and Docker Compose
  • Python 3 with pip, plus NumPy and Pillow for the inference client

Steps

  1. From the repository, change to models/vision/detection and build the Docker image with docker compose build.

  2. Run docker compose run --rm yolo-export to export the YOLO model and generate the Triton repository.

  3. Start the Triton server with docker compose up yolo-triton.

  4. Install the client dependencies NumPy and Pillow, then run python3 triton_client.py --endpoint localhost:8000.

Expected outcome

The example runs object-detection inference through Triton and writes results to output.jpg.

Guide limitations

  • This recipe is specific to the repository's YOLOv8 detection example.
  • The source documents the workflow but does not establish results on other hardware or software configurations.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Cloud AI SDKAdapt and run documented model recipes for computer-vision and NLP inference.Cloud, ServerThe GitHub repository is public. Its public visibility does not establish license terms.
TurboquantReplace a model’s existing inference cache with a compressed cache.Cloud, Linux, macOS, Self-hostedThe project describes itself as open source. The README documents installation through pip or from a source checkout.
GptqmodelQuantize a language model using calibration data and save the resulting checkpoint.CLI, Linux, macOS, Windows
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
qualcomm/cloud-ai-sdk · Official homepage title · retained in its source language
How we review sourcesSuggest a correction