Block floating point (BFP), an efficient numerical system for deep neural networks (DNNs),
achieves a good trade-off between dynamic range and hardware costs. Specifically, prior …

The demand for inference on extremely large scale LLMs has seen enormous growth in the
recent months. It made evident the colossal shortage of dedicated hardware capable of …

As energy consumption becomes a primary concern for deep learning acceleration, the
need to optimize not only data movement but also compute is becoming important. The …

The ever increasing sizes of Large Language Models (LLMs) beyond hundreds of billions of
parameters have generated enormous pressure on the manufacturers of dedicated …