All

742 repositories

NemoClaw
Public
Run agents like Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference
typescript nvidia sandboxing
typescript nvidia sandboxing ai-agents openclaw openshell
TypeScript
•
Apache License 2.0
•2.8k•21k•321•125•Updated Jun 5, 2026Jun 5, 2026
numbast
Public
Numbast is a tool to build an automated pipeline that converts CUDA APIs into Numba bindings.
cuda numba
cuda numba
C
•
Apache License 2.0
•22•62•44•13•Updated Jun 5, 2026Jun 5, 2026
TransformerEngine
Public
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwel…
python machine-learning deep-learning
python machine-learning deep-learning gpu cuda pytorch jax fp8 fp4
Python
•
Apache License 2.0
•739•3.4k•230•127•Updated Jun 5, 2026Jun 5, 2026
NeMo-Relay
Public
Multi-language agent runtime for execution scope management, lifecycle events, and middleware on tool and LLM calls.
Rust
•
Apache License 2.0
•26•53•2•8•Updated Jun 5, 2026Jun 5, 2026
flashdreams
Public
high-performance inference and serving library for interactive autoregressive video and world models
interactive efficiency world-models
interactive efficiency world-models video-models
Python
•
Other
•11•182•11•23•Updated Jun 5, 2026Jun 5, 2026
Megatron-LM
Public
Ongoing research training transformer models at scale
transformers model-para large-language-models
transformers model-para large-language-models
Python
•
Other
•4k•17k•355•479•Updated Jun 5, 2026Jun 5, 2026
aicr
Public
Tooling for optimized, validated, and reproducible GPU-accelerated AI runtime in Kubernetes
config kubernetes manifest
config kubernetes manifest ai runtime gpu helm argocd
Go
•
Apache License 2.0
•54•323•44•4•Updated Jun 5, 2026Jun 5, 2026
cccl
Public
CUDA Core Compute Libraries
cpp hpc gpu
cpp hpc gpu modern-cpp parallel-computing cuda nvidia gpu-acceleration cuda-kernels gpu-computing
C++
•
Other
•401•2.4k•1.3k•257•Updated Jun 5, 2026Jun 5, 2026
nv-rms-client
Public
NVIDIA Rack Management Service Rust language client crate
Rust
•
Apache License 2.0
•7•8•1•4•Updated Jun 5, 2026Jun 5, 2026
cuda-quantum
Public
C++ and Python support for the CUDA Quantum programming model for heterogeneous quantum-classical workflows
python cpp quantum
python cpp quantum quantum-computing hacktoberfest quantum-programming-language quantum-algorithms quantum-machine-learning unitaryhack
C++
•
Apache License 2.0
•399•1.1k•345•132•Updated Jun 5, 2026Jun 5, 2026
cudnn-frontend
Public
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
deep-learning gpu cuda
deep-learning gpu cuda nvidia transformer moe attention hopper cuda-kernels cuda-toolkit
Python
•
MIT License
•177•840•37•13•Updated Jun 5, 2026Jun 5, 2026
cosmos
Public
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infra…
Jupyter Notebook
•
Other
•584•9.1k•3•1•Updated Jun 5, 2026Jun 5, 2026
OpenShell
Public
OpenShell is the safe, private runtime for autonomous AI agents.
Rust
•
Apache License 2.0
•806•6.8k•165•59•Updated Jun 5, 2026Jun 5, 2026
cosmos-framework
Public
Our inference and training framework to run on the Cosmos Models
Python
•
Other
•12•157•2•7•Updated Jun 5, 2026Jun 5, 2026
infra-controller
Public
NVIDIA Infra Controller - Hardware Lifecycle Management and multitenant networking
Rust
•
Apache License 2.0
•110•182•273•40•Updated Jun 5, 2026Jun 5, 2026
TileGym
Public
Helpful kernel tutorials, examples and SKILLs for tile-based GPU programming
Python
•
Other
•71•745•4•5•Updated Jun 5, 2026Jun 5, 2026
NVSentinel
Public
NVSentinel is a cross-platform fault remediation service designed to rapidly remediate runtime node-level issues in GPU-accelerated computing environments
Go
•
Apache License 2.0
•85•306•32•13•Updated Jun 5, 2026Jun 5, 2026
spark-rapids-jni
Public
RAPIDS Accelerator JNI For Apache Spark
Cuda
•
Apache License 2.0
•81•56•90•15•Updated Jun 5, 2026Jun 5, 2026
TensorRT-LLM
Public
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inferen…
cuda pytorch moe
cuda pytorch moe blackwell llm-serving
Python
•
Other
•2.4k•14k•597•745•Updated Jun 5, 2026Jun 5, 2026
cuopt
Public
GPU accelerated decision optimization
gpu optimization cuda
gpu optimization cuda linear-programming
Cuda
•
Apache License 2.0
•188•931•130•31•Updated Jun 5, 2026Jun 5, 2026
gpu-driver-container
Public
The NVIDIA GPU driver container allows the provisioning of the NVIDIA driver through the use of containers.
Shell
•
Apache License 2.0
•84•169•8•18•Updated Jun 5, 2026Jun 5, 2026
Model-Optimizer
Public
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It comp…
Python
•
Apache License 2.0
•426•2.9k•56•201•Updated Jun 5, 2026Jun 5, 2026
spark-rapids-tools
Public
User tools for Spark RAPIDS
Scala
•
Apache License 2.0
•50•71•279•2•Updated Jun 5, 2026Jun 5, 2026
topograph
Public
A toolkit for discovering cluster network topology.
Go
•
Apache License 2.0
•21•130•6•2•Updated Jun 5, 2026Jun 5, 2026
cuda-python
Public
CUDA Python: Performance meets Productivity
Cython
•
Other
•294•3.3k•188•39•Updated Jun 5, 2026Jun 5, 2026
aistore
Public
AIStore: scalable storage for AI applications
kubernetes high-performance distributed-storage
kubernetes high-performance distributed-storage high-availability object-storage multi-cloud batch-jobs s3-compatible multipart-upload ml-training
Go
•
MIT License
•259•1.9k•1•1•Updated Jun 5, 2026Jun 5, 2026
IsaacTeleop
Public
The unified framework for sim & real robot teleoperation
Python
•
Apache License 2.0
•31•220•80•33•Updated Jun 5, 2026Jun 5, 2026
cudaqx
Public
Accelerated libraries for quantum-classical computing built on CUDA-Q.
C++
•
Other
•66•101•38•28•Updated Jun 5, 2026Jun 5, 2026
nv-config-manager
Public
NVIDIA Config Manager
Python
•
Apache License 2.0
•0•8•0•8•Updated Jun 5, 2026Jun 5, 2026
nvbmc-docs
Public
Documentation for Nvidia OpenBMC stack
TeX
•
Creative Commons Attribution 4.0 International
•9•36•1•1•Updated Jun 5, 2026Jun 5, 2026

ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

NVIDIA Corporation

All

All

742 repositories

NemoClaw

numbast

TransformerEngine

NeMo-Relay

flashdreams

Megatron-LM

aicr

cccl

nv-rms-client

cuda-quantum

cudnn-frontend

cosmos

OpenShell

cosmos-framework

infra-controller

TileGym

NVSentinel

spark-rapids-jni

TensorRT-LLM

cuopt

gpu-driver-container

Model-Optimizer

spark-rapids-tools

topograph

cuda-python

aistore

IsaacTeleop

cudaqx

nv-config-manager

nvbmc-docs

All

All

Repositories list

742 repositories