Boomerl

mml-book-chinese

《MATHEMATICS FOR MACHINE LEARNING》 一书的部分翻译。

Hands-on-RL

https://hrl.boyuai.com/

fun-rec

推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/

DeepCTR

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

AISystem

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

infer

A new tensorrt integrate. Easy to integrate many tasks

CUDA-Learn-Notes

🎉CUDA&C++ 笔记 / 大模型手撕CUDA / 技术博客，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.

CUDA-Programming-Guide-in-Chinese

This is a Chinese translation of the CUDA programming guide

TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

trt-samples-for-hackathon-cn

Simple samples for TensorRT programming

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

CUDA_Freshman

CUDA_gemm

A simple high performance CUDA GEMM implementation.

Tutorial

LLM Tutorial

CUDA-code

deep-learning-for-image-processing

deep learning for image processing including classification and object-detection etc.

llm-paper-daily

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Cpp-Design-Patterns

C++设计模式

tinyrpc

c++ async rpc framework. 14w+qps.

Semi-Supervised-Learning-Image-Classification

This library contains Semi-Supervised Learning Algorithms for Computer Vision tasks implemented with TensorFlow 2.x and Python 3.x

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

KuiperInfer

带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

leetcode-notes

🐳 LeetCode 算法笔记：面试、刷题、学算法。在线阅读地址：https://datawhalechina.github.io/leetcode-notes/

sweetalk-design-pattern

基于《大话设计模式》对设计原则和设计模式进行解读。

ColossalAI

Making large AI models cheaper, faster and more accessible

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

InternLM

Official release of InternLM2.5 7B base and chat models. 1M context support