About the author: I’m Saravanan Gnanaguru (gsaravanan.dev), part of the NVIDIA Developer Program. I read about NVIDIA technologies and publish articles here for others to consume.
A knowledge-sharing repository for NVIDIA technology learnings — organised by technology area, inspired by the NVIDIA Docs catalogue.
| Technology | Description |
|---|---|
| NVIDIA NIM | NVIDIA Inference Microservices — production-ready AI model serving |
| NVIDIA TensorRT | Deep learning inference optimization SDK for NVIDIA GPUs |
| NVIDIA Triton Inference Server | Multi-framework, multi-model scalable inference serving |
| NVIDIA NeMo Framework | End-to-end LLM training, fine-tuning, and customization |
| NVIDIA CUDA Toolkit | Foundational parallel computing platform for GPU-accelerated applications |
| NVIDIA RAPIDS | GPU-accelerated data science and machine learning for Python |
| NVIDIA cuDNN | GPU-accelerated deep neural network primitives library |
| NVIDIA API Catalog | Hosted AI model APIs and getting started guide for developers |
| AI Trends | Key AI topics and emerging trends for practitioners |
This repository is published as a GitHub Pages site at https://chefgs.github.io/nvidia_tech_guides via GitHub Actions whenever new content is pushed to the main branch.