A high-throughput and memory-efficient inference and serving engine for LLMs

Expert Parallelism Load Balancer

A curated list for Efficient Large Language Models

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient Multi-head Latent Attention Kernels

Awesome LLMs on Device: A Comprehensive Survey

Tensor library for machine learning

MLX: An array framework for Apple silicon

LLM inference in C/C++

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

The full minitorch student suite.

高性能计算相关知识学习笔记，包含学习笔记和相关知识的代码demo，在持续完善中。 如果有帮助的话请Star一下，对作者帮助很大，谢谢！

Pretrained Language Models for Source code

4 labs + 2 challenges + 4 docs

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

A list of awesome research on log analysis, anomaly detection, fault localization, and AIOps

量化研究-券商金工研报复现

基于Python的开源量化交易平台开发框架

🔥 Linux下C++轻量级WebServer服务器

中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)

音频可视化展示模块

Paper Lists for Graph Neural Networks