AWS Neuron

Latest news

1. 19 Oct
   Deepgram ports Nova-3 speech model to AWS Trainium2 for batch inference

   Deepgram worked with AWS Forward Deployed Engineering to port its Nova-3 speech-to-text model to AWS Trainium2 using the AWS Neuron stack. The effort involved kernel-level tuning and a data-parallel Rust runtime and produced measured throughput and cost results for offline batch transcription.

   Hardware · 1 source

   

Articles

No articles about AWS Neuron yet.