📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

AI and Memory Wall

DataLoom旨在提供复杂的数据转换以及分析服务，用户上传数据源（支持MySQL、API、Excel等），用户可以从多种数据源中创建数据集而不必在意数据维度的转换问题，数据集的创建支持自定义SQL以及AIGC一键创建，除此之外，DataLoom还支持LLM大模型进行自动化分析，也支持用户自定义分析目标生成数据分析报告。项目正在持续更新ing，点个Star持续关注，敬请期待

A ready-to-go translation ocr tool developed with WPF/WPF 开发的一款即用即走的翻译、OCR工具

File Converter is a very simple tool which allows you to convert and compress files using the context menu in windows explorer.

🦀️📸 Pure Rust tool to generate beautiful code snapshots, provide CLI and Library

机器学习&深度学习网站资源汇总（Machine Learning Resources）

The blog, read report and code example for AGI/LLM related knowledge.

AI Infra LLM infer/ tensorrt-llm/ vllm

real Transformer TeraFLOPS on various GPUs

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe

A highly optimized LLM inference acceleration engine for Llama and its variants.

Machine Learning Engineering Open Book

为独立开发者准备的精选技术栈和工具仓库来了！这里有你最需要的工具，帮你提升开发效率、节约成本，最重要的是——这些工具都是市场上热门的，经过验证的。🚀A curated collection of tech stacks and tools tailored for independent developers is here! these are proven, popular tools …

使用 CUDA C++ 实现的 llama 模型推理框架

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

(Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints" (https://arxiv.org/pdf/2305.13245.pdf)

SGLang is a fast serving framework for large language models and vision language models.

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

The GPU RAM Estimator provides a simple tool for estimating GPU memory usage during training and inference.

clash for unbuntu tutorial

Sourcetrail - free and open-source interactive source explorer

《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

Lightweight library for scraping web-sites with LLMs

本插件可以用于CSDN/知乎/脚本之家/博客园/掘金等网站,一键下载文章html或markdown文件;实现无需登录一键复制代码;支持选中代码;或者代码右上角按钮的一键复制;解除关注博主即可阅读全文提示;去除登录弹窗;去除跳转APP弹窗.

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组