Xelera Silva overcomes the latency drawback of machine learning algorithms based on XGBoost and LightGBM: The software enables users to take advantage of in-loop machine learning inference with ultra-low latency. Xelera Silva now includes a second acceleration variant: the Throughput-Optimized Flavor. The variant eliminates throughput bottlenecks with a best-in-class inference speed of 22M inferences per second.