Cast AI has launched an upgraded platform featuring new features including automated GPU-based machine selection and scaling for artificial intelligence development teams.
The system can scale computing resources for generative AI models more cost effectively. Among its new features, users can introduce automated provisioning for more economic graphics processing unit (GPU) instances, with automated decommissioning shipped once an instance's task is completed.
Users can also benefit from automated optimisation of Amazon Inferentia machines, while automated management of spot instances identifies optimal configuration for a model's computing requirements.
Cast AI identified cost savings of 76% in beta tests for an AI model.
Give a Pawfive to this post!
Share with your friends and followers
Start writing about what excites you in tech — connect with developers, grow your voice, and get rewarded.
Join other developers and claim your FAUN.dev() account now!
