NVIDIA

NVIDIA

NemoClaw

★ 22.463

Führen Sie Agenten wie Hermes, LangChain Deep Agents und OpenClaw mit verwalteter Inferenz sicherer in NVIDIA OpenShell aus.

NVIDIA

SkillSpector

★ 17.309

Sicherheitsscanner für KI-Agentenfähigkeiten. Erkennen Sie Schwachstellen, bösartige Muster und Sicherheitsrisiken.

NVIDIA

TensorRT-LLM

★ 14.627

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. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

NVIDIA

TensorRT

★ 13.348

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

NVIDIA

cutlass

★ 10.437

CUDA Templates and Python DSLs for High-Performance Linear Algebra

NVIDIA

garak

★ 9.258

the LLM vulnerability scanner

NVIDIA

OpenShell

★ 8.615

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

NVIDIA

warp

★ 7.117

Ein Python-Framework für GPU-beschleunigte Simulation, Robotik und maschinelles Lernen.

NVIDIA

DALI

★ 5.759

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

cuml

★ 5.277

NVIDIA cuML: GPU-Accelerated Machine Learning

NVIDIA

nccl

★ 5.092

Optimized primitives for collective multi-GPU communication

NVIDIA

GenerativeAIExamples

★ 4.181

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

NVIDIA

Model-Optimizer

★ 3.810

Eine einheitliche Bibliothek von SOTA-Modelloptimierungstechniken wie Quantisierung, Destillation, Bereinigung, neuronale Architektursuche, spekulative Dekodierung usw. Sie komprimiert Deep-Learning-Modelle für nachgelagerte Bereitstellungsframeworks wie TensorRT-LLM, TensorRT, vLLM usw., um die Inferenzgeschwindigkeit zu optimieren.

NVIDIA

TransformerEngine

★ 3.533

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 Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

NVIDIA

skills

★ 3.301

Projektüberblick: Agentenfähigkeiten für NVIDIA-Produkte, Installation in Claude Code, Codex und anderen Codierungsagenten, um Workflows für physische KI, Robotik, Simulation, CUDA und RAG durchgängig auszuführen. Fertigkeitskatalogprodukt | Beschreibung | Fähigkeiten | AIQ | NVIDIA AI-Q Blueprint – Stellen Sie lokale AI-Q-Dienste bereit und führen Sie flache oder tiefgreifende Forschungsworkflows als Agentenfähigkeiten aus.

NVIDIA

physicsnemo

★ 3.253

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

NVIDIA

NeMo-Agent-Toolkit

★ 2.632

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

NVIDIA

kvpress

★ 1.209

LLM KV cache compression made easy

NVIDIA

earth2studio

★ 1.131

Open-Source-Deep-Learning-Framework zum Erkunden, Erstellen und Bereitstellen von KI-Wetter-/Klima-Workflows.

NVIDIA

raft

★ 1.042

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.