NVIDIA-AI-Blueprints

NVIDIA's Python API for defining large language models and running optimized inference on NVIDIA GPUs.

NVIDIA SDK that optimizes trained deep learning models for low-latency inference on NVIDIA GPUs.

World foundation models, datasets, and tooling packaged together for physical AI and robotics work.

Real-time full-duplex speech-to-speech model with persona control via text role prompts and voice conditioning.

Reference architecture for GPU-accelerated vision agents that search, summarize, and answer questions about video.

Probes models at scale for jailbreaks, prompt injection, data leaks, hallucinations, and toxic output.

NVIDIA foundation model for generalist humanoid robots, with perception-to-action policies that transfer across bodies.

NVIDIA toolkit of KV-cache compression techniques that cut LLM memory use and extend context length.

AI weather and climate prediction workflows get built and deployed through this open-source deep-learning framework.

Neural vocoder from NVIDIA that synthesizes high-fidelity speech, music, and singing from mel-spectrograms.

NVIDIA's security scanner that inspects AI agent skills for vulnerabilities and malicious patterns.

Lightweight C++ inference engine that runs LLMs and vision-language models on edge devices.

Text normalization and inverse text normalization toolkit for ASR and TTS pipelines.

Rust proxy that routes LLM traffic across providers and translates OpenAI and Anthropic APIs.

NVIDIA GEAR Lab initiative applying world models to the robotics data problem in embodied AI training.

Collection of logits processors that customize LLM generation, working with vLLM, Hugging Face, and TensorRT-LLM.