Recent advances in energy harvesting and green communication technologies give rise to the emerging Internet of Battery-less Things (IoBT). With prolonged lifetime and dense deployment, IoBT-operated networks contain huge computational power that is not fully utilized. With time-varying renewable energy, it is non-trivial to process latency-sensitive tasks in IoBT networks. In this paper, we propose a novel in-network computing framework to efficiently process latency-sensitive tasks. At the beginning of each time slot, the proposed framework first conducts task capacity check to derive the upper bound of the input data size that can be processed within the deadline. Then, a latency-aware data partition algorithm is developed to minimize the overall latency by jointly considering the energy budget and node position. The real world energy harvesting profiles are used to evaluate the proposed method. The simulation results demonstrate that the proposed method achieves significantly lower latency compared with the existing strategies for IoBT systems with varying ambient energy generation.