~/nvidia-ncp-genl · LLM Architecture

← NVIDIA-Certified Professional Generative AI LLMs

NVIDIA · objective · 6% of the exam

LLM Architecture — NVIDIA-Certified Professional Generative AI LLMs

The official NVIDIA documentation our LLM Architecture practice questions are cited to. Review the primary sources, then practise.

practice 4 questions →

Official references for this objective

  • NvidiaTry NVIDIA NIM APIs

    Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
  • NvidiaScale and Serve Generative AI | NVIDIA Dynamo

    Separates large language model (LLM) context and generation phases across distinct GPUs, enabling independent GPU allocation and optimization to increase requests served per GPU.