NVIDIA Expands Its Deep Learning Inference Capabilities for Hyperscale Datacenters
Company Unveils NVIDIA TensorRT 4, TensorFlow Integration, Kaldi Speech Acceleration and Expanded ONNX Support; GPU Inference Now up to 190x Faster Than CPUs Tuesday, March 27, 2018 — GPU Technology Conference — NVIDIA today announced a series of new technologies and partnerships that expand its potential inference market to 30 million hyperscale servers worldwide, while dramatically […]
NVIDIA Expands Its Deep Learning Inference Capabilities for Hyperscale Datacenters Read More +










