Emergency communications networks require in-network intelligence for timely traffic handling under dynamic demands and runtime constraints. In these environments, packets may need different inference behaviors, and conventional model replacement via control-plane updates is too slow for responsive operation. We propose an in-network artificial computing framework with lightweight model-switching, where multiple Binary Neural Network (BNN) models are kept resident within a shared execution framework. Packet metadata selects the active model at packet granularity with O(1) selection cost. A fixed 1024-byte payload is aligned with x86 AVX-512, enabling efficient memory access. The framework is realized on an eBPF/XDP + AF_XDP stack. Experimental results show that the system sustains 1.894 Mpps with a 0.528 us inference latency, while model selection adds only 0.005 us. Our results demonstrate that different resident models induce distinct packet-processing behaviors, that scaling to 16 slots preserves low switching overhead, and that online model switching completes without wrong-verdict packets. These results show the practicality of lightweight in-network artificial computing on commodity hardware.

翻译：应急通信网络需要网络内智能能力，以在动态需求与运行时约束下实现及时的流量处理。在此类环境中，数据包可能要求不同的推理行为，而通过控制平面更新实现的传统模型替换方案因响应速度过慢而无法胜任。我们提出了一种具备轻量级模型切换能力的网络内人工智能计算框架，该框架将多个二值神经网络（BNN）模型共置于同一执行框架内。数据包元数据以O(1)的选择开销在数据包粒度上激活目标模型。固定1024字节的载荷与x86 AVX-512指令集对齐，可实现高效的内存访问。该框架基于eBPF/XDP + AF_XDP协议栈实现。实验结果表明：系统在0.528微秒推理延迟下可维持1.894 Mpps的吞吐量，而模型选择仅增加0.005微秒的额外开销。实验结果验证了不同驻留模型会引发差异化的数据包处理行为，将插槽扩展至16个时仍能保持低切换开销，且在线模型切换过程不会产生错误判决数据包。上述结果证明了在商用硬件上实现轻量级网络内人工智能计算的可行性。