VMware by Broadcom Private AI Foundation
Joint Gen AI platform
Build and Deploy Private and Secure Gen AI Models
Unlock Gen AI and unleash productivity with this joint Gen AI platform. Address privacy, choice, cost, performance, and compliance concerns.
Guided Deployment
- Get significantly increased deployment speed with guided deployment of workload domain and associated components.
Vector Databases for Enabling RAG Workflows
- Enable fast querying of data and real-time updates to enhance the outputs of LLMs with vector databases enabled by pgvector on PostgreSQL.
Catalog Setup Wizard
- Simplify infrastructure provisioning of complex projects with curated and optimized AI infrastructure catalog items.
GPU Monitoring
- Get optimized performance and costs by streamlining GPU usage with visibility of GPU resource utilization across clusters and hosts.
Deep Learning VM Templates
- Improve the consistency of your environment with preconfigured deep learning VMs.
NVIDIA Nemo Retriever
- Enhance RAG capabilities with a collection of NVIDIA CUDA-X Gen AI microservices enabling organizations to seamlessly connect custom models to diverse business data.
NVIDIA NIM Operator
- Simplify RAG application deployment using NVIDIA AI workflows examples into production, without rewriting code.
NVIDIA NIM
- Get seamless AI inferencing at scale with a set of easy-to-use microservices designed to speed up the deployment of Gen AI across enterprises.
NVIDIA GPU Operator
- Automate lifecycle management of the software required to use GPUs with Kubernetes. Improve GPU performance, utilization, and telemetry.