ARCHLEXOSS

AWS · AI & Machine Learning

AI/ML Model Inference Pipeline

CloudFront and API Gateway feeding Lambda preprocessor to EKS GPU inference cluster backed by ElastiCache and S3. This diagram is written in ArchLex and passes AWS provider checks.

Edit in the playgroundAWS diagrams as code
AI/ML Model Inference Pipeline: CloudFront and API Gateway feeding Lambda preprocessor to EKS GPU inference cluster backed by ElastiCache and S3AI/ML Model Inference Pipeline: CloudFront and API Gateway feeding Lambda preprocessor to EKS GPU inference cluster backed by ElastiCache and S3
provider aws
direction LR
validation normal

cdn: cloudfront
gateway: api-gateway
preprocessor: lambda
inference_cluster: eks
feature_store: elasticache
model_bucket: s3

cdn > gateway > preprocessor
preprocessor -[invokes]->|submits inference| inference_cluster
inference_cluster -[reads]->|feature data| feature_store
inference_cluster -[reads]->|model artifacts| model_bucket

What is in this diagram.

Resources

Relationships

Render it yourself.

Save the source as ai-ml-inference.arch and render it with the CLI, or ask your agent to adapt it through the ArchLex MCP server.

npx @archlex/cli render ai-ml-inference.arch --output ai-ml-inference.svg

All examples