Nvidia announces TensorRT 8, slashes BERT inference times down to a millisecond
Tweet Providing over twice the precision and inference speed compared to the last generation, Nvidia’s new TensorRT 8 deep learning …
BERT
NVIDIA registers the world’s quickest BERT training time and largest transformer-based model
Tweet The company’s immensely powerful DGX SuperPOD trains BERT-Large in a record-breaking 53 minutes and trains GPT-2 8B, the world’s …