LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.
-
Updated
Sep 16, 2025 - Python
LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
DISTWAR atomic reduction optimization on "3D Gaussian Splatting for Real-Time Radiance Field Rendering".
A memory profiler for NVIDIA GPUs to explore memory inefficiencies in GPU-accelerated applications.
Fundamentals of heterogeneous parallel programming with CUDA C/C++ at the beginner level.
RocAuc Pairiwse objective for gradient boosting
bilibili视频【CUDA 12.x 并行编程入门(Python版)】配套代码
Spiral's Machine Learning Library
Building upon original repo, trying to implement encoder-decoder transformer using CUDA
GPU porgamming CUDA is the repo that has all the list of my materials that I used for the CUDA . I learned CUDA myself and this material helped me get the basic strong .
Una piccola AI che il suo picco massimo di risposta è stato di 0.02 secondi di risposta | Konata ~ 2025
Pygame-powered version of the classic board game with an intelligent AI opponent with multiplayer mode support.
A fun CUDA/QT Mandelbrot explorer with selection zoom to the limit of C double precision, accumulated thumbnails, back to any previous screen, and screen save capabilities.
The "NutBoltClassifier" system represents a significant leap forward in automated fastener classification, harnessing deep learning and computer vision techniques.
Image grayscale parallel implementation using Cuda and python
Detector Reconocedor de Patentes en tiempo real (Cámaras IP o videos) utilizando Redes Neuronales Convolucionales con soporte a MySQL
This is an AI-powered stock trading bot that uses neural networks to predict market trends and execute trades via the Alpaca API. Built with PyTorch for GPU acceleration.
(Year 2016) Spell checking is a well-studied NLP task focused on detecting and correcting spelling errors in text. Common approaches include rule-based, dictionary-based, and statistical methods, widely used in word processing and text correction.
ASC Homework 1-3
Add a description, image, and links to the cuda-programming topic page so that developers can more easily learn about it.
To associate your repository with the cuda-programming topic, visit your repo's landing page and select "manage topics."