MoE 相关的热门 GitHub AI项目仓库
发现与 MoE 相关的最受欢迎的开源项目和工具，了解最新的开发趋势和创新。
SGLang is a fast serving framework for large language models and vision language models.
sgl-projectUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, GLM4, Mistral, Yi1.5, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, DeepSeek-VL2, Phi4, GOT-OCR2, ...).
modelscope:electron: An unofficial https://bgm.tv ui first app client for Android and iOS, built with React Native. 一个无广告、以爱好为驱动、不以盈利为目的、专门做 ACG 的类似豆瓣的追番记录，bgm.tv 第三方客户端。为移动端重新设计，内置大量加强的网页端难以实现的功能，且提供了相当的自定义选项。 目前已适配 iOS / Android / WSA、mobile / 简单 pad、light / dark theme、移动端网页。
czy0729
一款开源简洁高颜值的酷狗第三方客户端 An open-source, concise, and aesthetically pleasing third-party client for KuGou that supports Windows / macOS / Linux :electron:
iAJueMoe counter badge with multiple themes! - 多种风格可选的萌萌计数器
journey-ad
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
deepseek-aiA family of open-sourced Mixture-of-Experts (MoE) Large Language Models
XueFuzhaoYour best Genshin Impact companion! Help you plan what to farm with ascension calculator and database. Also track your progress with todo and wish counter.
MadeBaruna
PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538
davidmrau
Speech synthesis model /inference GUI repo for galgame characters based on Tacotron2, Hifigan, VITS and Diff-svc
luoyily⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)
pjlab-sys4nlpTutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek FP8/FP4
microsoftAdan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
sail-sgA toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
open-compassA customizable colorful eye-candy theme for Emacser. Moe, moe, kyun!
kuanyui
The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"
HITsz-TMGAn open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案，包含从训练到推理的完整代码和脚本，以及实践中积累一些经验和结论。)
ScienceOne-AIA curated reading list of research in Mixture-of-Experts(MoE).
codecaution
Reverse image search tool (SauceNao, IQDB, Ascii2D, trace.moe, and more)
DecimationSatania IS the BEST waifu, no really, she is, if you don't believe me, this website will convince you
Pizzacus
[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"
Time-MoE
This Telegram Bot can tell the anime when you send an screenshot to it
sorulyMindSpore online courses: Step into LLM
mindspore-courses
😘 A pinterest-style layout site, shows illusts on pixiv.net order by popularity.
kokororin🖼二次元图片下载器 Pics downloader for booru sites,Pixiv.net,Bilibili.com,Konachan.com,Yande.re , behoimi.org, safebooru, danbooru,Gelbooru,SankakuComplex,Kawainyan,MiniTokyo,e-shuushuu,Zerochan,WorldCosplay ,Yuriimg etc.
xpluskyOpen Source firmware replacement for Tuya Wifi Thermostate from Beca and Moes with Home Assistant Autodiscovery
fashberg:dancer: Anime tracker, database and community. Moved to https://git.akyoto.dev/web/notify.moe
animenotifierA Free and Open Source Java Framework for Multiobjective Optimization
MOEAFrameworkA Telegram bot that imports LINE/kakao stickers or creates/manages new sticker set.
star-39Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch
lucidrains
moe SS Front End for https://github.com/mengskysama/shadowsocks/tree/manyuser
wzxjohnImplementation of Soft MoE, proposed by Brain's Vision team, in Pytorch
lucidrainsAn application specialized in image super-resolution for ACGN illustrations and Visual Novel CG. 专注于插画/Galgame CG等ACGN领域的图像超分辨率的应用
TeamMoeAIA Python library for the state-of-the-art Bayesian optimization algorithms, with the core implemented in C++.
wujian16
Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).
inferflowTrue coroutines for PHP>=8.1 without worrying about event loops and callbacks.
moebiusphpTrue coroutines for PHP>=8.1 without worrying about event loops and callbacks.
moebiusphpTrue coroutines for PHP>=8.1 without worrying about event loops and callbacks.
moebiusphp
ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward experts. We released a collection of ModuleFormer-based Language Models (MoLM) ranging in scale from 4 billion to 8 billion parameters.
IBM[ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
SkyworkAICode for paper "Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters" CVPR2024
JiazuoYu[ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
efeslab