Stars
Ongoing research training transformer models at scale
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
推荐系统入门指南,全面介绍了工业级推荐系统的理论知识(王树森推荐系统公开课-基于小红书的场景讲解工业界真实的推荐系统),如何基于TensorFlow2训练模型,如何实现高性能、高并发、高可用的Golang推理微服务。Comprehensively introduced the theory of industrial recommender system, how to trainning …
A throughput-oriented high-performance serving framework for LLMs
存放JAVA开发的设计思想、算法:《剑指Offer》、《编程珠玑》、《深入理解Java虚拟机:JVM高级特性与最佳实践》、《重构-改善既有代码的设计 中文版》、《clean_code(中文完整版)》、《Java编程思想(第4版)》、《Java核心技术 卷I (第8版)》、《Quartz_Job+Scheduling_Framework》;一些大的上传不上来的文件在README
Open deep learning compiler stack for cpu, gpu and specialized accelerators
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
《神经网络与深度学习》 邱锡鹏著 Neural Network and Deep Learning
Summary of some awesome work for optimizing LLM inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
Effective Java(第3版)各章节的中英文学习参考(已完成)
It is open source ebook about TensorFlow kernel and implementation mechanism.
A library for efficient similarity search and clustering of dense vectors.
Book_7_《机器学习》 | 鸢尾花书:从加减乘除到机器学习;欢迎批评指正
A curated list of resources dedicated to federated learning.
deeplearning.ai(吴恩达老师的深度学习课程笔记及资源)
该仓库尝试整理推荐系统领域的一些经典算法模型