tools
AMD Enterprise AI Suite (SiloGen)
Open-source Kubernetes software stack for deploying, managing, and scaling AI workloads on AMD compute.
In inglese
AMD Enterprise AI Suite, now presented by AMD as the Enterprise AI Reference Stack, connects AI frameworks, models, inference services, developer tools, and resource management on Kubernetes. It supports model deployment, inference, fine-tuning, workspaces, solution blueprints, monitoring, scheduling, and access control.
It is intended for infrastructure administrators, AI developers, researchers, and organizations running enterprise AI workloads on AMD hardware. AMD does not publish software pricing on the product page; hardware, cloud infrastructure, and support may cost extra.
Features
- Open-source modular architecture for enterprise AI workloads
- AMD Inference Microservices with OpenAI-compatible APIs
- Hardware-aware inference configuration and autoscaling
- Low-code AI Workbench for AIM deployment and fine-tuning
- Developer workspaces with notebooks, IDEs, and SSH access
- Solution Blueprints packaged as Kubernetes Helm charts
- Resource scheduling, quotas, monitoring, and access control
- Programmatic APIs with OpenAPI specifications
Use cases
- Deploy AI models for production inference on AMD hardware
- Fine-tune and evaluate models using AI Workbench
- Schedule GPU and CPU workloads across teams and projects
- Launch RAG chatbots, coding assistants, and agentic workflows
- Monitor compute utilization and manage model deployments
- Build self-hosted enterprise AI platforms on Kubernetes
Pros
Cons
Latest updates
- Version: 2.2.2 (2.2.2)
Fixed a first-boot race condition; added support for a custom Envoy Gateway HTTPS port.
- Version: 2.2.1 (2.2.1)
Fixed custom-model onboarding on Radeon clusters and inference metrics for AIMs on EPYC; improved ROCm version detection.
- Version: 2.2 (2.2)
AIMs run across Instinct GPUs, Radeon Pro GPUs, and EPYC CPUs; adds Envoy AI Gateway, SeaweedFS, model onboarding, and API access.
- Version: 2.1.1 (2.1.1)
AIM catalogue updated with models; ROCm 7.2.3 enabled for all 0.11 AIMs; Solution Blueprints catalog updated.
- Version: 2.1 (2.1)
AI Workbench adds fine-tuning of AIMs and image input in ChatUI; Resource Manager adds configurable idle workload pre-emption.
Capabilities
- Command line — “workspaces and CLI reference workloads for the expert users.” source
- Self-hosted — “from bare metal compute to production-grade AI in minutes” source
- API — “Supports OpenAI-compatible APIs and open weight models, enabling rapid deployment without re-engineering.” source
- Runs models for you — “Prebuilt inference containers that bundle model, engine, and optimized configuration for AMD hardware.” source
- Builds agents and workflows — “such as agentic workflows, document summarization, RAG chatbots, and AI coding assistants.” source
- Search over your data — “such as agentic workflows, document summarization, RAG chatbots, and AI coding assistants.” source
- Traces and evaluates — “Observability and model management through real-time monitoring dashboards and life cycle management of models and keys.” source
Get it
Pricing
- Starting price
- Free
- Prices checked
- 2026-09-24
- Read
- by web search
AMD Enterprise AI Suite
Free
- Modular open-source platform with four components: Solution Blueprints, Inference Microservices (AIMs), AI Workbench, Resource Manager
- Prebuilt optimized containers for AMD hardware, OpenAI-compatible APIs, open models
- Dynamic workspaces, fine-tuning pipelines, inference deployment
- Intelligent workload scheduling, quota management, telemetry for GPU utilization
- Kubernetes-native, enterprise security (SSO, RBAC), no vendor lock-in
- Accelerates from bare metal/cloud to production AI in minutes on AMD Instinct GPUs