nvdia

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

Deep CNN for learning image restoration without clean data!

Native Adobe Photoshop hybrid plugin (UXP Frontend + C++ Native Backend) that implements NVIDIA's DLSS 5 Neural Rendering pipeline for static 2D images.

A Flexible and High-Performance Inference Serving Engine for Open Diffusion Language Models

An interactive, agentic data analysis application that leverages advanced LLM reasoning to help users explore, visualize, and understand their data.

NVR with realtime local object detection for IP cameras（增加tensorRT yolov5/8及中文支持）

TERRADRONE-SIM is a weather-aware survey-drone flight lab, mission planner, and 6-DOF physics simulator modeled around the DJI P4 Multispectral and FAA 14 CFR 107.51(c) regulations. It pulls hourly ensemble forecasts for a field's exact weather using NVIDIA Earth-2 StormCast-CONUS

Benchmarking several NVIDIA GPUs with dorado

DermaDetectAI is a Flask app for detecting skin diseases using deep learning. Developed by Ranit Manik and team, it includes models for identifying 5, 10, and 23 skin conditions, and supports NVIDIA GPU acceleration. The models are trained with PyTorch.

RAG with LlamaIndex and NVIDIA

GPU-accelerated llama-cpp-python 0.3.16 wheel for Python 3.14 (CUDA 13.1, Windows)

AI-powered multilingual translation platform built with Python and Streamlit, supporting seamless translation across multiple languages using modern AI technologies.

A rag model , kind off chat gpt.... Still working on back-end nd realtime data extraction.

YouTube video link into notes.

Autonomous multi-agent software engineering engine — Planner, Researcher, Coder, Executor, Reviewer pipeline built with FastAPI, LangGraph, and OpenAI-compatible LLMs

High-performance, offline speech-to-text CLI utilities written in Rust. Features static FFmpeg linking and local ONNX model evaluation using NVIDIA Parakeet and Nemotron for batch and streaming recognition across 40+ languages.

Runnable reference implementation of execution finality for AI-native 5G/6G, IMT-2030, AI-RAN and O-RAN. Covers Candidate Acts, PED validation, evidence-before-authority, scoped non-bearer capabilities, Finality Sink verification, replay/epoch controls, RIC/UPF variations, tests and benchmarks. Keywords: 3GPP, RAN, telecom security.

🧠 The Final Battle for Placement — A complete preparation repository covering DSA, System Design, Core CS subjects, and interview problem-solving. The last step toward mastering fundamentals and cracking top placements. - "Preparation is not about perfection — it’s about progress, persistence, and purpose."