liminn

liminn's Stars

• deepseek-ai/DeepSeek-V3

  Language:Python95.2k74249815.4k

• xai-org/grok-1

  Grok open release

  Language:Python50.2k6142218.4k

• bannedbook/fanqiang

  翻墙-科学上网

  Language:Kotlin39.4k1.2k7847.3k

• karpathy/LLM101n

  LLM101n: Let's build a Storyteller

  33.1k3.1k01.8k

• mem0ai/mem0

  The Memory layer for AI Agents

  Language:Python27.3k1467962.6k

• harry0703/MoneyPrinterTurbo

  利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

  Language:Python25.9k2034623.8k

• hiddify/hiddify-app

  Multi-platform auto-proxy client, supporting Sing-box, X-ray, TUIC, Hysteria, Reality, Trojan, SSH etc. It’s an open-source, secure and ad-free.

  Language:Dart20.4k1581.3k1.8k

• kyleneideck/BackgroundMusic

  Background Music, a macOS audio utility: automatically pause your music, set individual apps' volumes and record system audio.

  Language:C++17.1k150682697

• KindXiaoming/pykan

  Kolmogorov Arnold Networks

  Language:Jupyter Notebook15.6k1124421.5k

• KwaiVGI/LivePortrait

  Bring portraits to life!

  Language:Python14.5k1264201.6k

• kvcache-ai/ktransformers

  A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

  Language:Python13.4k111753926

• Huanshere/VideoLingo

  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

  Language:Python12.2k803431.2k

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++10.1k1112.4k1.3k

• imbushuo/mac-precision-touchpad

  Windows Precision Touchpad Driver Implementation for Apple MacBook / Magic Trackpad

  Language:C9.5k192516602

• MrKai77/Loop

  Window management made elegant.

  Language:Swift8k30458168

• hiddify/Hiddify-Manager

  Multi-user anti-filtering panel, with an effortless installation and supporting more than 20 protocols to circumvent filtering plus the telegram proxy.

  Language:Python7k682.4k801

• InternLM/MindSearch

  🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

  Language:JavaScript6.3k45201632

• gpu-mode/lectures

  Material for gpu-mode lectures

  Language:Jupyter Notebook4.2k6210422

• NVlabs/Sana

  SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

  Language:Python3.9k77191242

• VectorSpaceLab/OmniGen

  OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

  Language:Jupyter Notebook3.9k86166335

• kvcache-ai/Mooncake

  Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

  Language:C++3k3093194

• gpt-omni/mini-omni2

  Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

  Language:Python1.7k7061192

• lichao-sun/Mora

  Mora: More like Sora for Generalist Video Generation

  Language:Python1.6k8012103

• roncoo/roncoo-education

  领课教育系统（roncoo-education）是基于领课网络多年的在线教育平台开发和运营经验打造出来的产品，致力于打造一个各行业都适用的分布式在线教育系统。系统采用前后端分离模式，前台采用vue.js为核心框架，后台采用Spring Cloud为核心框架。系统目前主要功能有课程点播功能，支持多家视频云的接入，课程附件管理功能，支持多家存储云的接入，讲师管理功能，支持讲师入驻功能，可以帮助个人或者企业快速搭建一个轻量级的在线教育平台。

  Language:Java1.4k6010565

• Ghost-Clocker/V2raySSSSRShare

  科学上网，vpn机场推荐，支持shadowrocket，ss, ssr, v2ray, trojan, clash,clashr,需要自取（每日更新）

  1.2k7061

• 1zilc/fishing-funds

  基金,大盘,股票,虚拟货币状态栏显示小应用,基于Electron开发,支持MacOS,Windows,Linux客户端,数据源来自天天基金,蚂蚁基金,爱基金,腾讯证券等

  Language:TypeScript9309155101

• triton-inference-server/tensorrtllm_backend

  The Triton TensorRT-LLM Backend

  Language:Python81722545119

• Mellanox/nccl-rdma-sharp-plugins

  RDMA and SHARP plugins for nccl library

  Language:C185211934

• RWKV/rwkv-onnx

  A converter and basic tester for rwkv onnx

  Language:Python42384

• DefTruth/Awesome-LLM-Inference

  📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism, etc. 🎉🎉

  7001