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.

    12.3k 955

  2. NemoClaw NemoClaw Public

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

    TypeScript 23k 3.2k

  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. Tensor…

    Python 15.1k 2.9k

  4. cutlass cutlass Public

    CUDA Templates and Python DSLs for High-Performance Linear Algebra

    C++ 10.7k 2.2k

  5. warp warp Public

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

    Python 7.3k 689

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

    NVIDIA Linux open GPU kernel module source

    C 17.6k 2k

Repositories

Showing 10 of 839 repositories
  • xla_staging Public Forked from openxla/xla

    A machine learning compiler for GPUs, CPUs, and ML accelerators

    NVIDIA/xla_staging's past year of commit activity
    C++ 5 Apache-2.0 1,017 0 0 Updated Nov 10, 2026
  • Model-Optimizer Public

    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.

    NVIDIA/Model-Optimizer's past year of commit activity
    Python 5,583 Apache-2.0 806 101 372 Updated Nov 10, 2026
  • NeMo-Fabric Public

    NVIDIA NeMo Fabric

    NVIDIA/NeMo-Fabric's past year of commit activity
    Python 74 Apache-2.0 45 46 14 Updated Nov 10, 2026
  • Nomos Public

    Stops AI agents from taking unwanted or overeager actions. Nomos reviews each proposed action against the agent's own context (its permissions, task, justification, blast radius and signed receipts of what it has observed) using OPA policy and an LLM council. Approved actions get a signed, single-use Writ; the executor runs exactly that.

    NVIDIA/Nomos's past year of commit activity
    Python 21 Apache-2.0 2 9 31 Updated Nov 10, 2026
  • OpenShell Public

    OpenShell is the safe, private runtime for autonomous AI agents.

    NVIDIA/OpenShell's past year of commit activity
    Rust 21,370 Apache-2.0 2,090 418 (2 issues need help) 231 Updated Nov 10, 2026
  • cuml Public

    NVIDIA cuML: GPU-Accelerated Machine Learning

    NVIDIA/cuml's past year of commit activity
    Python 5,319 Apache-2.0 688 743 (1 issue needs help) 47 Updated Nov 10, 2026
  • cuda-python Public

    CUDA Python: Performance meets Productivity

    NVIDIA/cuda-python's past year of commit activity
    Cython 3,412 Apache-2.0 348 226 (4 issues need help) 107 Updated Nov 10, 2026
  • cccl Public

    CUDA Core Compute Libraries

    NVIDIA/cccl's past year of commit activity
    C++ 2,573 551 1,473 (5 issues need help) 428 Updated Nov 10, 2026
  • cudf Public

    cuDF - GPU DataFrame Library

    NVIDIA/cudf's past year of commit activity
    C++ 9,798 Apache-2.0 1,161 1,253 (36 issues need help) 252 Updated Nov 10, 2026
  • structured-data-models Public

    Foundation Models for Structured Data

    NVIDIA/structured-data-models's past year of commit activity
    Python 479 Apache-2.0 50 8 52 Updated Nov 10, 2026