✨✨VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

An elegent pytorch implement of transformers

Cross Beat (xbe.at) - Your hub for python, machine learning and AI tutorials. Explore Python tutorials, AI insights, and more.

A modular graph-based Retrieval-Augmented Generation (RAG) system

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Example models using DeepSpeed

UnderstandingDeepLearing中文翻译

ONNX-TensorRT: TensorRT backend for ONNX

how to optimize some algorithm in cuda.

LLM101n: Let's build a Storyteller

Material for cuda-mode lectures

Accelerate Model Training with PyTorch 2.X, published by Packt

Slides, notes, and materials for the workshop (cuda-mode)

📰 Must-read papers and blogs on Speculative Decoding ⚡️

LLM全栈优质资源汇总

Examples for using ONNX Runtime for machine learning inferencing.

A demo of image classification with PyTorch DDP (DistributedDataParallel) and AMP (Automatic Mixed Precision) modules.

Codes & examples for "CUDA - From Correctness to Performance"

Awesome LLM compression research papers and tools.

Research and Materials on Hardware implementation of Transformer Model

The official GitHub page for the survey paper "A Survey of Large Language Models".

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.

Understanding Deep Learning - Simon J.D. Prince

Achieve a tiny STL in C++11

Puck is a high-performance ANN search engine

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。