An accessible diagram and text description of the seven-layer AI runtime stack.
Audience: All readersReading time: 1 minuteStatus: FoundationalLast reviewed:
The seven-layer diagram separates hardware, kernels, compilers, inference, serving, agentic execution, and product workflow responsibilities. The diagram is paired with a complete text description and does not rely on color alone.
Seven-layer AI runtime stack
The runtime stack separates hardware, kernels, compilation, inference, serving, agentic control, and product workflow responsibilities.Text description
A vertical stack of seven numbered layers. Layer 0 is hardware and system substrate. Layer 1 is kernels and hardware libraries. Layer 2 is the compiler and graph runtime. Layer 3 is the model and LLM inference engine. Layer 4 is serving and distributed execution. Layer 5 is the agentic and application runtime. Layer 6 is the product and workflow layer. Cross-cutting identity, security, observability, evaluation, cost, and evidence concerns apply across the stack.
