Sold by: DEEPX CO.,LTD.
Deployed on AWS
- The DEEPX Solution is a software product that offers a streamlined, end-to-end workflow for deploying deep learning models to edge devices. It uses a serverless compilation pipeline to automatically trigger the deployment of NPU packages, enabling businesses to quickly and efficiently manage and remotely trigger AI/ML demos on IoT devices.
Overview
The solution provides a streamlined, end-to-end workflow for mass deployment of deep learning models to the edge. It leverages a serverless compilation pipeline that is automatically triggered by ONNX model uploads, followed by the deployment of NPU packages (drivers runtime, and models) to edge devices via AWS IoT Greengrass. This enables efficient management and remote triggering of AI/ML demos on IoT devices.
Highlights
- Effortless Deployment: Our solution provides a streamlined workflow for the mass deployment of deep learning models directly to edge devices, simplifying the process from compilation to delivery.
- Accelerate Innovation: Empower your business to quickly and efficiently deploy AI models at the edge, reducing operational overhead and accelerating time-to-value.
- Automated and Scalable: Leverage a serverless pipeline that automatically deploys deep learning models to your IoT devices, enabling efficient management and remote demos at scale.
Details
Sold by
Categories
Delivery method
Delivery option
DX Compiler Serverless Orchestrated
Latest version
Operating system
Ubuntu 22.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Vendor refund policy
N/A
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
DX Compiler Serverless Orchestrated
This CloudFormation template deploys an event-driven DX Compiler pipeline using a pre-built AMI (Ubuntu 22.04, Python 3.10) with dxcom CLI, calibration dataset, and AWS CLI already installed -- no runtime downloads or installations required.
Workflow:
- Upload an ONNX file paired with a JSON config file to the created S3 bucket.
- S3 event triggers a Lambda function that starts a Step Functions state machine.
- Step Functions launches a temporary EC2 instance from the pre-built DX Compiler AMI.
- AWS Systems Manager (SSM) downloads the model and config, runs dxcom compilation, and uploads the compiled DXNN artifact back to S3.
- The EC2 instance self-terminates on success; on failure, the workflow forcibly terminates it for cost control.
Features:
- Pre-built AMI with all dependencies -- zero installation at compile time
- Event-driven compilation (no always-on servers)
- Deterministic shutdown and cost efficiency
- Retry and failure handling (EC2 launch and SSM command execution)
- No inbound network ports opened (outbound-only security group)
- IAM roles follow least-privilege: EC2 has scoped S3 + SSM + self-terminate only
- Marketplace-compliant parameterization (ImageId, VPC/Subnet, InstanceType supplied by buyer)
- GPU instance types supported (g4ad, g4dn, g5, g6) for accelerated compilation
Use Cases: Automated model build pipelines, batch conversion of ONNX assets, reproducible compiler runs.
CloudFormation Template (CFT)
AWS CloudFormation templates are JSON or YAML-formatted text files that simplify provisioning and management on AWS. The templates describe the service or application architecture you want to deploy, and AWS CloudFormation uses those templates to provision and configure the required services (such as Amazon EC2 instances or Amazon RDS DB instances). The deployed application and associated resources are called a "stack."
Version release notes
Compiler Upgrade
- Upgraded from the legacy dx-com binary (/opt/dx_com/dx_com -input ... -output ..., over 1 year old) to the modern Python-based dxcom CLI (dxcom -m ... -c ... -o ./)
- Enables config-driven compilation with full control over quantization, target hardware, and optimization parameters through a JSON config file ONNX + JSON Config Pair Trigger
- Previously, uploading a single .onnx file triggered compilation with hardcoded parameters
- Now requires both an .onnx model and a .json config file to be present in the same S3 directory before starting
- Lambda trigger listens for both file types and searches the same directory for the counterpart
- If the pair is incomplete, the event is skipped -- prevents premature execution
- Duplicate execution protection added -- uploading the same file pair multiple times will not create redundant workflow runs Original Filenames Preserved
- In v2.2.0, downloaded files were renamed to model.onnx and the output was always {model_name}_compiled.dxnn
- In v2.3.0, original filenames are preserved throughout the pipeline
- Compiled .dxnn output is uploaded to the same S3 directory as the source files with the filename generated by dxcom Security and Networking
- Only HTTPS/443 outbound traffic to AWS services (S3, SSM, CloudWatch) is required
- Removed HTTP/80 egress rule
- Public IP assignment is no longer forced -- instance respects the subnet's own configuration
- Enables fully private deployments using VPC endpoints without any internet access
- IAM permissions tightened to least-privilege across all roles Instance Type Updates
- Removed t3.large and c5.large as they are insufficient for compilation workloads
- Added t3a.xlarge, t2.xlarge, g4ad.xlarge, g4dn.xlarge, g5.xlarge, and g6.xlarge
- Supports both CPU and GPU-accelerated compilation Infrastructure Changes
- Root EBS volume explicitly set to 30GB gp3, providing sufficient space for model compilation workspace
- Boot wait reduced from 120 seconds to 60 seconds
- AMI is automatically provided by AWS Marketplace -- no manual AMI ID configuration needed
Additional details
Usage instructions
- Deploy the stack. Provide: ImageId (prefilled by Marketplace), VpcId & SubnetId (must have outbound access to S3 + SSM endpoints), unique S3 bucket name (ModelBucketName), InstanceType (default t3.xlarge; use GPU types for large models).
- After CREATE_COMPLETE, navigate to the Outputs tab for ModelBucketName and StateMachineArn.
- Upload an ONNX file paired with a JSON config file (e.g. mymodel.onnx + mymodel.json) to the bucket root.
- A Step Functions execution starts automatically (triggered by S3 event via Lambda).
- Wait for the compiled artifact (suffix _compiled.dxnn) to appear in the same bucket.
- Monitor progress: AWS Console > Step Functions > State machine ARN (from Outputs).
- All EC2 instances terminate automatically on both success and failure paths.
- To compile again, upload more ONNX + JSON file pairs.
Support
Vendor support
Email: info@deepx.ai Support URL: https://deepx.ai/contact-us/ We are committed to helping our customers succeed with their AI projects. Our support includes:
- Dedicated Technical Assistance: Get expert guidance on a wide range of topics, including product integration, developer questions, and model optimization.
- Comprehensive Resources: We provide access to a developer portal, quick-start guides, and online video courses to help you get up and running quickly.
- Scalable Support Plans: Whether you're a developer prototyping with the DX TechBridge Kit or a business transitioning to mass production, we offer tailored support plans to meet your specific needs and ensure seamless deployment.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.