New techniques efficiently accelerate sparse tensors for massive AI models | MIT News
5 Mins read
Researchers from MIT and NVIDIA have developed two techniques that accelerate the processing of sparse tensors, a type of data structure that’s…
Accelerating AI tasks while preserving data security | MIT News
4 Mins read
With the proliferation of computationally intensive machine-learning applications, such as chatbots that perform real-time language translation, device manufacturers often incorporate specialized hardware…