Skip to content
@NVIDIA

NVIDIA Corporation

Pinned Loading

  1. cosmos 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 infrastructure, and more.

    Jupyter Notebook 11.9k 894

  2. NemoClaw NemoClaw Public

    Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

    TypeScript 22.6k 3.1k

  3. TensorRT-LLM 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 inference efficiently on NVIDIA GPUs. Tensorโ€ฆ

    Python 14.7k 2.8k

  4. cutlass cutlass Public

    CUDA Templates and Python DSLs for High-Performance Linear Algebra

    C++ 10.5k 2.1k

  5. warp warp Public

    A Python framework for GPU-accelerated simulation, robotics, and machine learning.

    Python 7.2k 631

  6. open-gpu-kernel-modules open-gpu-kernel-modules Public

    NVIDIA Linux open GPU kernel module source

    C 17.4k 1.9k

Repositories

Showing 10 of 808 repositories
  • NeMo-Fabric Public

    NVIDIA NeMo Fabric

    NVIDIA/NeMo-Fabric's past year of commit activity
    Python 43 Apache-2.0 26 6 9 Updated Sep 28, 2026
  • kvpress Public

    LLM KV cache compression made easy

    NVIDIA/kvpress's past year of commit activity
    Python 1,219 Apache-2.0 183 3 4 Updated Sep 28, 2026
  • nvcf Public

    Platform for deploying and routing GPU-accelerated inference, streaming, and batch workloads at scale.

    NVIDIA/nvcf's past year of commit activity
    Go 226 Apache-2.0 76 356 112 Updated Sep 28, 2026
  • k8s-test-infra Public

    Simulate NVIDIA infrastructure (e.g. GPU) on CPU nodes in Kubernetes โ˜•๏ธ

    NVIDIA/k8s-test-infra's past year of commit activity
    Go 66 Apache-2.0 39 110 42 Updated Sep 28, 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.

    NVIDIA/cudnn-frontend's past year of commit activity
    Python 950 Apache-2.0 297 105 87 Updated Sep 28, 2026
  • mig-parted Public

    MIG Partition Editor for NVIDIA GPUs

    NVIDIA/mig-parted's past year of commit activity
    Go 264 Apache-2.0 74 5 4 Updated Sep 28, 2026
  • cccl Public

    CUDA Core Compute Libraries

    NVIDIA/cccl's past year of commit activity
    C++ 2,525 506 1,641 (9 issues need help) 329 Updated Sep 28, 2026
  • cuopt Public

    GPU accelerated decision optimization

    NVIDIA/cuopt's past year of commit activity
    Cuda 1,052 Apache-2.0 238 184 72 Updated Sep 28, 2026
  • DALI Public

    A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

    NVIDIA/DALI's past year of commit activity
    C++ 5,767 Apache-2.0 680 190 (24 issues need help) 35 Updated Sep 28, 2026
  • NemoClaw Public

    Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

    NVIDIA/NemoClaw's past year of commit activity
    TypeScript 22,556 Apache-2.0 3,118 595 (2 issues need help) 117 Updated Sep 28, 2026