LLM inference in C/C++

程序员延寿指南 | A programmer's guide to live longer

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

Some awesome comfyui workflows in here, and they are built using the comfyui-easy-use node package.

how to optimize some algorithm in cuda.

OpenAI Triton backend for Intel® GPUs

PyTorch native quantization and sparsity for training and inference

A repository dedicated to evaluating the performance of quantizied LLaMA3 using various quantization methods..

Float 16/32 Converter

Run Generative AI models with simple C++/Python API and using OpenVINO Runtime

📚 Solutions to Introduction to Algorithms Third Edition

This collection of samples demonstrates best practices to achieve optimal video quality and performance on Intel GPUs for content delivery networks. Check out our demo, recommended command lines an…

Universal LLM Deployment Engine with ML Compilation

A toolkit showing GPU's all-round capability in video processing

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

Apply cnocr to achieve conversion from image to excel file

An efficient video loader for deep learning with smart shuffling that's super easy to digest

Code repository of all OpenGL chapters from the book and its accompanying website https://learnopengl.com

NVIDIA Linux open GPU kernel module source

Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.

Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions

oneAPI Level Zero Specification Headers and Loader

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Examples for the usage of "pybind11"

Seamless operability between C++11 and Python

Intel® Video Processing Library (Intel® VPL) API, dispatcher, and examples