Write For Us

Conversational AI Inference at Data Center Scale

Sponsored Post Vitamin D2 Canada Persia
131 Views
Published
"Announcing #NVIDIAJarvis beta program, which offers leading deep learning models, delivers intelligent, human-like responses in less than 300 ms on SpeechSquad. SpeechSquad is a new benchmark that measures end-to-end response time in conversational #AI networks. Jarvis is 2X as fast as simple models running on a CPU system that end up costing 3X as much to operate.

Sign up for Jarvis Beta program: https://nvda.ws/3nnqsU3

SpeechSquad benchmark repo on GitHub: https://github.com/NVIDIA/speechsquad
Watch the full GTC 2020 keynote: https://nvda.ws/30Fa4Vl
Category
Hardware
Tags
NVIDIA
Sign in or sign up to post comments.
Be the first to comment