Affinity Scheduling Policies

Table 1 describes the characteristics and resource usage rules of an inference server (with Atlas 300I inference cards).

**Table 1** Affinity policies
Policy Name	Policy Description
Affinity scheduling by inference card	The Ascend AI Processor within the same Atlas 300I inference card is preferentially selected. If one to four Ascend AI Processors need to be allocated, ensure that the processor(s) is (are) selected from a single Atlas 300I inference card. The node with one available Ascend AI Processor is the best, with three being the next best option, followed by two, and lastly four.

Parent topic: Inference Server (with Atlas 300I Inference Cards)