Seldon Core+ builds on the open-source Seldon Core framework by adding enterprise-grade support, warranties, and expert services tailored for production-grade ML deployments. Core+ offers platform-agnostic deployment across Kubernetes, Docker, or Docker Compose, and multi-model serving with autoscaling, canary rollout, A/B testing, and real-time monitoring. Backed by Seldon IQ accelerator sessions, dedicated support with SLAs, and an annual health check, Core+ ensures model governance, traceability, compliance, and reliability—critical for regulated industries like finance, healthcare, and automotive. Ideal for ML teams seeking to scale efficiently while maintaining operational control and reducing risk.

Features:

• Enterprise warranties & SLAs: Supported binaries with guaranteed uptime and issue resolution.
• Dedicated Success Management: Personalized onboarding, check-ins, and support via a Customer Success Manager.
• Accelerator Programs (IQ): Includes workshops, training, and strategic sessions from Seldon IQ.
• Platform-agnostic deployment: Supports Kubernetes, Docker Compose, and service meshes.
• Multi-model serving & overcommit: Deploy multiple models per server with efficient memory use.
• Advanced rollout strategies: Canary, A/B tests, experiments, and shadow deployments out-of-the-box.
• Autoscaling & resource tuning: Supports Kubernetes HPA, partial scheduling, and adaptive scaling.
• Traceability & observability: Full audit logs, metrics, explainers, and drift detection with integrations (Prometheus, Grafana, Alibi).
• LLM module add-on: Deploy GenAI models with prompt management, memory, retrieval, and function calling.
• Annual Health Check: Expert evaluation for optimization, upgrades, and best practice alignment.