Sizing Guide
NVIDIA Blueprint - PDF to Podcast
NVIDIA Blueprints are comprehensive reference workflows built with NVIDIA AI libraries, SDKs, and microservices for speeding up the deployment of AI solutions. This toolkit uses the PDF to podcast blueprint that leverages large language models (LLMs), text-to-speech, and NVIDIA NIM microservices to build a generative AI application that transforms PDF data into audio content.
NVIDIA NIM provides containers to self-host GPU-accelerated inferencing microservices for pretrained and customized AI models across clouds and data centers. NIM microservices expose industry-standard APIs for simple integration into AI applications, development frameworks, and workflows. Built on pre-optimized inference engines from NVIDIA and the community, including NVIDIA® TensorRT™ and TensorRT-LLM, NIM microservices optimize response latency and throughput for each combination of foundation model and GPU. NVIDIA NIM for Developer is the edition used in this toolkit.
The NIM microservices used in this toolkit:
Llama 3.1 8B Instruct
Server Configuration
2U NVIDIA-Certified System
Intel Xeon Platinum 8480+ @3.8GHz Turbo (Sapphire Rapids) HT
3.84 TB Solid State Drive (NVMe)
Intel Ethernet Controller X710 for 10GBASE-T
1x NVIDIA GPU: L40S/L40
Hypervisor - VMware ESXi 8.0.3 (for Linux virtual workstation)
Hypervisor - Windows Server 2025 (for Windows virtual workstation)
NVIDIA Host Driver - 550.144.02 (for Linux virtual workstation)
NVIDIA Host Driver - 572.60 (for Windows virtual workstation)
Linux virtual workstation:
OS Version - Ubuntu 24.04
16 vCPU
32GB vRAM
NVIDIA vGPU Guest Driver - 550.144.03
NVIDIA vGPU Profile - 48Q
Windows virtual workstation:
OS Version - Windows 11
16 vCPU
32GB vRAM
NVIDIA vGPU Guest Driver - 572.60
NVIDIA vGPU Profile - 48Q