代码库
Linux patch review and testing CLI with a multi-stage agentic workflow
Rust
Generate structured output for OCR tasks from latex documents using nvtexlive
Python
Documentation builder for NVIDIA products
Python
An SDK (Software Development Kit) for building commercial-grade, AI-native, 3GPP, and O-RAN compliant 5G/6G gNB software on NVIDIA-accelerated computing platforms.
C++
Accelerated ETL toolkit for building AI-ready datasets across multiple scientific and engineering domains
Python
SOMA BVH to humanoid robot motion retargeting library built with Newton and NVIDIA Warp
Python
character-animationhumanoid-robotshumanoidsretargeting-motion
This repository provides a starter kit for sports intelligence built on NVIDIA AI stack: playbooks, training recipes, and inference for Multimodal Language Models.
Python
llmmultimodal-deep-learningmultimodal-large-language-modelsmultimodal-llmnemotronnemotron-3-nano-30b-playbookssportssports-analyticssports-tech
Build and run Docker containers leveraging NVIDIA GPUs
cudadockergpunvidia-docker
DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models
Jupyter Notebook
ALCHEMI Toolkit is a developer toolkit for accelerating training and inference for AI in chemistry and material science.
Python
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
Jupyter Notebook
gpu-accelerationlarge-language-modelsllmllm-inferencemicroservicenemoragretrieval-augmented-generationtensorrttriton-inference-server
CUDA Python: Performance meets Productivity
Cython
Documentation for Nvidia OpenBMC stack
TeX
Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.
Rust
agentsaiatifatofclaude-codecodexdeepagentshermes-agentlangchainlanggraphmiddlewarenvidiaobservabilityopenclawopeninferenceoptimizationotelruntimesecurity
NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs
C++
cuVS - a library for vector search and clustering on the GPU
Cuda
annsclusteringcudadistancegpuinformation-retrievalllmmachine-learningnearest-neighborsneighborhood-methodssimilarity-searchsparsestatisticsvector-searchvector-similarityvector-store
Router that virtually distributes inference across connected devices in the home.
Go
JAX-Toolbox
Python
ALCHEMI Toolkit-Ops is a collection of optimized batch kernels to accelerate computational chemistry and material science workflows.
Python
high-performance inference and serving library for interactive autoregressive video and world models
Python
efficiencyinteractivevideo-modelsworld-models