Applied AI experiments and examples for PyTorch

Production First and Production Ready End-to-End Speech Recognition Toolkit

Accessible large language models via k-bit quantization for PyTorch.

Development repository for the Triton language and compiler

High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程

What are learned in tiktoken?

A minimal GPU design in Verilog to learn how GPUs work from the ground up

基于C++开发的视频行为分析系统v4系统，可以在不用考虑音视频开发，编解码开发，界面开发等情况下， 只需要训练自己的模型，开发自己的算法插件，就可以轻松实现出任何想要的视频行为检测，比如周界入侵，烟火检测，打架，斗殴，跌倒，人群聚集，电动车，垃圾箱，抽烟，攀爬，离岗睡岗，安全帽，充电桩，工作服， 疲劳检测，交通拥堵等等。

参加华为AscendC算子编程比赛的代码

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

camera pipeline

A place to record memories, knowledge and ideas | 记录回忆，知识和畅想的地方

Open Neural Network Compiler

属于每个人的公众号”查特查特“上线啦！新问题、新方法、新发现，欢迎提PR！

opencv-mobile 通过调整编译参数，删减部分opencv源码，来最小化编译的 opencv 库提供了 opencv 常用的功能，如读写图片，处理，矩阵操作等等 版本与上游同步，无第三方依赖在绝大多数情况下，以 1/10 的体积无痛替换官方 opencv，尤其适合对体积有特殊要求的移动端和嵌入式环境

学习安全运营的记录 | The knowledge base of security operation

Hackable and optimized Transformers building blocks, supporting a composable construction.

A parser, editor and profiler tool for ONNX models.

Inference code for LLaMA models

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, s…

AI学习之路

fast log and exp functions for x86/x64 SSE

ESJZone 的小說備份

An unofficial cuda assembler, for all generations of SASS, hopefully ：）