NVlabs

NVlabs

tiny-cuda-nn

★ 4,536

Lightning fast C++/CUDA neural network framework

NVlabs

Eagle

★ 3,568

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

NVlabs

nvdiffrec

★ 2,298

Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

NVlabs

MambaVision

★ 2,231

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

NVlabs

SoL-Pi

★ 2,095

SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses

NVlabs

alpamayo

★ 2,020

NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.

NVlabs

sionna

★ 1,606

Sionna: An Open-Source Library for Research on Communication Systems

NVlabs

alpasim

★ 1,234

AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies

NVlabs

Fast-dLLM

★ 1,088

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

NVlabs

DoRA

★ 997

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

NVlabs

ToolOrchestra

★ 766

ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

NVlabs

OmniVinci

★ 679

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

NVlabs

QeRL

★ 519

[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

NVlabs

SpatialClaw

★ 379

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning