{"version":"0.11.0","built_at":"2026-10-12T01:17:59.374Z","license":"CC BY 4.0 © Mike Reams","canonical":"https://catalog.mikereams.com","category":{"id":"TR-110.50","name":"Model Serving & Inference","description":"Running trained models behind an endpoint with scaling, batching and monitoring of what they predict.","aliases":["Inference Serving","Model Deployment"],"in_scope":["Online and batch inference","GPU scheduling","Prediction monitoring"],"capability_ids":["BC-770.20.30","BC-770.20.40","BC-770.50.10"],"examples":["KServe","vLLM","NVIDIA Triton Inference Server","BentoML"],"out_of_scope":[],"domain_id":"TR-110","domain":"AI & Machine Learning","page_url":"https://catalog.mikereams.com/technology/TR-110.50","business_capabilities":[{"id":"BC-770.20.30","name":"Model Deployment & Serving"},{"id":"BC-770.20.40","name":"Model Monitoring & Retraining"},{"id":"BC-770.50.10","name":"AI Platform Operations"}],"technology_ids":["TE-kserve"]},"domain":{"id":"TR-110","name":"AI & Machine Learning","description":"The models, platforms and plumbing behind machine learning and generative AI, from training to agents in production.","category_ids":["TR-110.10","TR-110.20","TR-110.30","TR-110.40","TR-110.50"],"page_url":"https://catalog.mikereams.com/technology#TR-110"},"technologies":[{"id":"TE-kserve","name":"KServe","kind":"platform","page_url":"https://catalog.mikereams.com/technology/TE-kserve"}]}