NVIDIA

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

1 plugin · NVIDIA/Model-Optimizer

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

3 plugins · NVIDIA/skills

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

1 plugin · NVIDIA/earth2studio

GPU accelerated decision optimization

9 plugins · NVIDIA/cuopt

NVIDIA Kaggle Plugin gives agents end-to-end Kaggle competition workflows through a single skill, nvidia-kaggle-skill. It can gather competition context, study public writeups and notebooks, reproduce kernels locally, submit to competitions, and manage Ka

1 plugin · NVIDIA/nvidia-kaggle

From PyTorch model to end-to-end TensorRT inference experience in two commands—AI-native, cross-platform, and built for the best possible user experience.

1 plugin · NVIDIA/TensorRT-Model-Connect

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

1 plugin · NVIDIA/NeMo-Relay