Hybrid multi-cloud computing provider Nutanix has partnered with NVIDIA to integrate the latter's NIM inference microservices with Nutanix's GPT-in-a-Box 2.0 technology. This allows third-party enterprises to build scalable GenAI solutions in a public cloud and at the edge.
GPT-in-a-Box 2.0, expected to be available in the latter half of 2024, will automate deployment and inference for a range of AI models (open-source community models, NVIDIA AI Foundation models, and custom models). Additionally, Nutanix announced a certification for NVIDIA’s AI Enterprise 5.0 platform, which streamlines the development and deployment of production-grade AI, including NVIDIA NIM.
Analyst QuickTake: The collaboration enhances Nutanix’s original GPT-in-a-Box solution, launched in August 2023 , by integrating NVIDIA’s NIM for inference. The platform provided software infrastructure for deploying and fine-tuning large language models (LLMs) using leading open-source AI and MLOps frameworks.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.