Abstract: Techniques discussed herein include dynamically providing synchronous and/or asynchronous data processing by a machine-learning model service. The machine-learning model service (“the service”) executes a stream manager application, a web interface, and a machine-learning model via a common container. The stream manager application can obtain input data (e.g., from an input data stream, a partition of an input data stream, etc.) and provide the data to the machine-learning model through the web interface using a local communication channel (e.g., a loopback interface that bypasses local network interface hardware of the computing device on which the model executes). Prediction results from the model may be provided as output data (e.g., to an output data stream, to a partition of an output data stream, etc.).

Abstract: An output buffer circuit is disclosed that has optimized ground bounce characteristics while maintaining low propagation delay. The output buffer may be incorporated within an integrated circuit and may be embodied in either inverting or non-inverting and in either enabling and non-enabling configurations. The output buffer circuit includes a feedback means coupled to the output terminal of the output buffer and to a pull-down transistor. The feedback means provides a feedback voltage to the gate of the pull-down transistor to regulate the derivative of source current with respect to time. The feedback means includes a pair of field effect transistors and either an inverter gate or a NOR gate coupled across one of the feedback field effect transistors.