| 1 |
vllm |
65271 |
11926 |
Python |
1868 |
A high-throughput and memory-efficient inference and serving engine for LLMs |
2025-12-13T03:34:24Z |
| 2 |
LLaMA-Factory |
63892 |
7739 |
Python |
812 |
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) |
2025-12-12T17:44:29Z |
| 3 |
sglang |
21241 |
3732 |
Python |
633 |
SGLang is a fast serving framework for large language models and vision language models. |
2025-12-13T03:41:38Z |
| 4 |
TensorRT-LLM |
12381 |
1943 |
Python |
569 |
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. |
2025-12-13T03:44:27Z |
| 5 |
ms-swift |
11608 |
1049 |
Python |
806 |
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, …) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Phi4, …) (AAAI 2025). |
2025-12-12T10:06:38Z |
| 6 |
Bangumi |
5027 |
157 |
TypeScript |
23 |
: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。 |
2025-12-12T21:36:34Z |
| 7 |
xtuner |
5024 |
393 |
Python |
233 |
A Next-Generation Training Engine Built for Ultra-Large MoE Models |
2025-12-12T04:20:07Z |
| 8 |
trace.moe |
4885 |
260 |
None |
0 |
Anime Scene Search by Image |
2025-10-10T13:31:43Z |
| 9 |
MoeKoeMusic |
4388 |
278 |
Vue |
7 |
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 / Web :electron: |
2025-12-06T02:45:05Z |
| 10 |
flashinfer |
4209 |
593 |
Cuda |
256 |
FlashInfer: Kernel Library for LLM Serving |
2025-12-13T03:31:39Z |
| 11 |
Moeditor |
4130 |
273 |
JavaScript |
106 |
(discontinued) Your all-purpose markdown editor. |
2020-07-07T01:08:32Z |
| 12 |
fastllm |
4108 |
413 |
C++ |
311 |
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。 |
2025-12-04T06:57:15Z |
| 13 |
GLM-4.5 |
3297 |
342 |
Python |
27 |
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models |
2025-12-03T03:07:26Z |
| 14 |
Moe-Counter |
2658 |
273 |
JavaScript |
4 |
Moe counter badge with multiple themes! - 多种风格可选的萌萌计数器 |
2025-08-12T08:16:18Z |
| 15 |
MoeGoe |
2398 |
245 |
Python |
27 |
Executable file for VITS inference |
2023-08-22T07:17:37Z |
| 16 |
MoE-LLaVA |
2284 |
140 |
Python |
65 |
【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models |
2025-07-15T07:59:33Z |
| 17 |
ICEdit |
2046 |
113 |
Python |
27 |
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run! |
2025-11-12T17:28:10Z |
| 18 |
MoBA |
2011 |
127 |
Python |
10 |
MoBA: Mixture of Block Attention for Long-Context LLMs |
2025-04-03T07:28:06Z |
| 19 |
Cortex |
2009 |
151 |
Python |
4 |
个人构建MoE大模型：从预训练到DPO的完整实践 |
2025-12-10T10:08:18Z |
| 20 |
DeepSeek-MoE |
1850 |
295 |
Python |
17 |
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models |
2024-01-16T12:18:10Z |
| 21 |
fastmoe |
1824 |
197 |
Python |
27 |
A fast MoE impl for PyTorch |
2025-02-10T06:04:33Z |
| 22 |
moemail |
1759 |
1129 |
TypeScript |
34 |
一个基于 NextJS + Cloudflare 技术栈构建的可爱临时邮箱服务🎉 | A cute temporary email service built with NextJS + Cloudflare technology stack 🎉 |
2025-12-09T18:34:50Z |
| 23 |
OpenMoE |
1641 |
83 |
Python |
6 |
A family of open-sourced Mixture-of-Experts (MoE) Large Language Models |
2024-03-08T15:08:26Z |
| 24 |
paimon-moe |
1492 |
274 |
JavaScript |
303 |
Your best Genshin Impact companion! Help you plan what to farm with ascension calculator and database. Also track your progress with todo and wish counter. |
2025-12-03T01:03:02Z |
| 25 |
MOE |
1319 |
140 |
C++ |
170 |
A global, black box optimization engine for real world metric optimization. |
2023-03-24T11:00:32Z |
| 26 |
moepush |
1227 |
332 |
TypeScript |
11 |
一个基于 NextJS + Cloudflare 技术栈构建的可爱消息推送服务, 支持多种消息推送渠道✨ |
2025-05-10T11:42:44Z |
| 27 |
SpikingBrain-7B |
1216 |
162 |
Python |
7 |
Spiking Brain-inspired Large Models, integrating hybrid efficient attention, MoE modules and spike encoding into its architecture |
2025-12-01T11:13:32Z |
| 28 |
mixture-of-experts |
1211 |
110 |
Python |
6 |
PyTorch Re-Implementation of “The Sparsely-Gated Mixture-of-Experts Layer” by Noam Shazeer et al. https://arxiv.org/abs/1701.06538 |
2024-04-19T08:22:39Z |
| 29 |
Aria |
1085 |
91 |
Jupyter Notebook |
31 |
Codebase for Aria - an Open Multimodal Native MoE |
2025-01-22T03:25:37Z |
| 30 |
Uni-MoE |
1045 |
63 |
Python |
26 |
Uni-MoE: Lychee’s Large Multimodal Model Family. |
2025-12-12T04:49:21Z |
| 31 |
llama-moe |
998 |
64 |
Python |
6 |
⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024) |
2024-12-06T04:47:07Z |
| 32 |
MoeTTS |
996 |
77 |
None |
0 |
Speech synthesis model /inference GUI repo for galgame characters based on Tacotron2, Hifigan, VITS and Diff-svc |
2023-03-03T07:30:05Z |
| 33 |
Tutel |
948 |
106 |
C |
54 |
Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4 |
2025-12-12T07:25:00Z |
| 34 |
MoeMemosAndroid |
917 |
98 |
Kotlin |
86 |
An app to help you capture thoughts and ideas |
2025-11-30T06:08:51Z |
| 35 |
moebius |
873 |
48 |
JavaScript |
40 |
Modern ANSI & ASCII Art Editor |
2024-05-02T15:54:35Z |
| 36 |
Time-MoE |
846 |
89 |
Python |
11 |
[ICLR 2025 Spotlight] Official implementation of “Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts” |
2025-12-12T08:11:45Z |
| 37 |
Hunyuan-A13B |
809 |
118 |
Python |
24 |
Tencent Hunyuan A13B (short as Hunyuan-A13B), an innovative and open-source LLM built on a fine-grained MoE architecture. |
2025-07-08T08:45:27Z |
| 38 |
Adan |
804 |
70 |
Python |
4 |
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models |
2025-06-08T14:35:41Z |
| 39 |
DeepSeek-671B-SFT-Guide |
782 |
94 |
Python |
1 |
An 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。) |
2025-03-13T03:51:33Z |
| 40 |
MixtralKit |
773 |
76 |
Python |
12 |
A toolkit for inference and evaluation of ‘mixtral-8x7b-32kseqlen’ from Mistral AI |
2023-12-15T19:10:55Z |
| 41 |
moe-theme.el |
762 |
65 |
Emacs Lisp |
15 |
A customizable colorful eye-candy theme for Emacser. Moe, moe, kyun! |
2025-05-27T06:12:05Z |
| 42 |
moe |
691 |
35 |
Nim |
82 |
A command line based editor inspired by Vim. Written in Nim. |
2025-12-12T04:52:00Z |
| 43 |
Awesome-Mixture-of-Experts-Papers |
653 |
44 |
None |
1 |
A curated reading list of research in Mixture-of-Experts(MoE). |
2024-10-30T07:48:14Z |
| 44 |
SmartImage |
653 |
32 |
C# |
7 |
Reverse image search tool (SauceNao, IQDB, Ascii2D, trace.moe, and more) |
2025-11-05T18:12:53Z |
| 45 |
MoeMemos |
649 |
59 |
Swift |
70 |
An app to help you capture thoughts and ideas |
2025-12-01T16:20:57Z |
| 46 |
moedict-webkit |
637 |
101 |
Objective-C |
102 |
萌典網站 |
2025-10-07T06:22:07Z |
| 47 |
vtbs.moe |
629 |
36 |
Vue |
32 |
Virtual YouTubers in bilibili |
2025-07-31T13:39:09Z |
| 48 |
satania.moe |
611 |
55 |
HTML |
3 |
Satania IS the BEST waifu, no really, she is, if you don’t believe me, this website will convince you |
2022-10-09T23:19:01Z |
| 49 |
moebius |
610 |
43 |
Elixir |
3 |
A functional query tool for Elixir |
2024-10-23T18:55:45Z |
| 50 |
MoeList |
609 |
20 |
Kotlin |
30 |
Another unofficial Android MAL client |
2025-12-07T11:47:06Z |
| 51 |
Chinese-Mixtral |
609 |
43 |
Python |
0 |
中文Mixtral混合专家大模型（Chinese Mixtral MoE LLMs） |
2024-04-30T04:29:06Z |
| 52 |
moebooru |
578 |
81 |
Ruby |
26 |
Moebooru, a fork of danbooru1 that has been heavily modified |
2025-11-18T06:29:28Z |
| 53 |
MoeGoe_GUI |
571 |
68 |
C# |
8 |
GUI for MoeGoe |
2023-08-22T07:32:08Z |
| 54 |
trace.moe-telegram-bot |
544 |
79 |
JavaScript |
0 |
This Telegram Bot can tell the anime when you send an screenshot to it |
2025-12-03T12:18:09Z |
| 55 |
moerail |
503 |
40 |
JavaScript |
16 |
铁路车站代码查询 × 动车组交路查询 |
2025-08-13T12:55:25Z |
| 56 |
MiniMind-in-Depth |
499 |
45 |
None |
4 |
轻量级大语言模型MiniMind的源码解读，包含tokenizer、RoPE、MoE、KV Cache、pretraining、SFT、LoRA、DPO等完整流程 |
2025-06-16T14:13:15Z |
| 57 |
step_into_llm |
480 |
124 |
Jupyter Notebook |
36 |
MindSpore online courses: Step into LLM |
2025-11-19T02:22:45Z |
| 58 |
LPLB |
457 |
25 |
Python |
0 |
An early research stage expert-parallel load balancer for MoE models based on linear programming. |
2025-11-19T07:20:35Z |
| 59 |
MOE |
422 |
75 |
Java |
18 |
Make Opensource Easy - tools for synchronizing repositories |
2022-06-20T22:41:08Z |
| 60 |
hydra-moe |
415 |
16 |
Python |
10 |
None |
2023-11-02T22:53:15Z |
| 61 |
DiT-MoE |
410 |
19 |
Python |
7 |
Scaling Diffusion Transformers with Mixture of Experts |
2024-09-09T02:12:12Z |
| 62 |
InferenceMAX |
392 |
61 |
Python |
62 |
Open Source Continuous Inference Benchmarking - GB200 NVL72 vs MI355X vs B200 vs H200 vs MI325X & soon™ TPUv6e/v7/Trainium2/3/GB300 NVL72 - DeepSeek 670B MoE, GPTOSS |
2025-12-12T22:19:44Z |
| 63 |
MoeLoaderP |
388 |
26 |
C# |
11 |
🖼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. |
2025-05-19T13:20:58Z |
| 64 |
st-moe-pytorch |
374 |
33 |
Python |
4 |
Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch |
2024-06-17T00:48:47Z |
| 65 |
Awesome-Efficient-Arch |
371 |
31 |
None |
0 |
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models |
2025-11-11T09:47:37Z |
| 66 |
pixiv.moe |
368 |
41 |
TypeScript |
0 |
😘 A pinterest-style layout site, shows illusts on pixiv.net order by popularity. |
2023-03-08T06:54:34Z |
| 67 |
moe-sticker-bot |
367 |
38 |
Go |
32 |
A Telegram bot that imports LINE/kakao stickers or creates/manages new sticker set. |
2024-06-06T15:28:28Z |
| 68 |
WThermostatBeca |
366 |
73 |
C++ |
4 |
Open Source firmware replacement for Tuya Wifi Thermostate from Beca and Moes with Home Assistant Autodiscovery |
2023-08-26T22:10:38Z |
| 69 |
MoeSR |
358 |
9 |
JavaScript |
7 |
An 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 |
2025-08-06T14:15:38Z |
| 70 |
MOEAFramework |
350 |
128 |
Java |
0 |
A Free and Open Source Java Framework for Multiobjective Optimization |
2025-12-04T23:53:12Z |
| 71 |
notify.moe |
350 |
45 |
Go |
86 |
:dancer: Anime tracker, database and community. Moved to https://git.akyoto.dev/web/notify.moe |
2022-09-26T07:15:05Z |
| 72 |
dialogue.moe |
339 |
11 |
Python |
1 |
None |
2022-12-14T14:50:38Z |
| 73 |
soft-moe-pytorch |
337 |
9 |
Python |
4 |
Implementation of Soft MoE, proposed by Brain’s Vision team, in Pytorch |
2025-04-02T12:47:40Z |
| 74 |
awesome-moe-inference |
314 |
11 |
None |
0 |
Curated collection of papers in MoE model inference |
2025-10-20T01:30:05Z |
| 75 |
moell-blog |
303 |
80 |
PHP |
2 |
基于 Laravel 开发，支持 Markdown 语法的博客 |
2022-07-31T11:51:54Z |
| 76 |
MoH |
299 |
15 |
Python |
4 |
MoH: Multi-Head Attention as Mixture-of-Head Attention |
2024-10-29T15:22:54Z |
| 77 |
moeSS |
298 |
107 |
PHP |
11 |
moe SS Front End for https://github.com/mengskysama/shadowsocks/tree/manyuser |
2015-02-27T08:44:30Z |
| 78 |
moe |
278 |
46 |
Scala |
18 |
An -OFun prototype of an Ultra Modern Perl 5 |
2013-09-27T18:39:18Z |
| 79 |
android-app |
276 |
27 |
Kotlin |
5 |
Official LISTEN.moe Android app |
2025-12-10T03:45:18Z |
| 80 |
Cornell-MOE |
272 |
64 |
C++ |
25 |
A Python library for the state-of-the-art Bayesian optimization algorithms, with the core implemented in C++. |
2020-02-04T18:39:37Z |
| 81 |
parameter-efficient-moe |
272 |
16 |
Python |
1 |
None |
2023-10-31T19:21:15Z |
| 82 |
MoE-Infinity |
265 |
20 |
Python |
13 |
PyTorch library for cost-effective, fast and easy serving of MoE models. |
2025-10-15T17:52:58Z |
| 83 |
GRIN-MoE |
264 |
13 |
None |
0 |
GRadient-INformed MoE |
2024-09-25T18:46:48Z |
| 84 |
MoE-Adapters4CL |
259 |
23 |
Python |
8 |
Code for paper “Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters” CVPR2024 |
2025-09-18T08:38:29Z |
| 85 |
MoE-plus-plus |
257 |
13 |
Python |
1 |
[ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts |
2024-10-16T06:21:31Z |
| 86 |
MoeQuest |
251 |
76 |
Java |
1 |
The meizi of a material design style welfare App. |
2017-02-14T14:13:53Z |
| 87 |
inferflow |
250 |
23 |
C++ |
8 |
Inferflow is an efficient and highly configurable inference engine for large language models (LLMs). |
2024-03-15T06:52:33Z |
| 88 |
fiddler |
248 |
29 |
Python |
2 |
[ICLR’25] Fast Inference of MoE Models with CPU-GPU Orchestration |
2024-11-18T00:25:45Z |
| 89 |
MoeLoader-Delta |
246 |
36 |
C# |
52 |
Improved branching version of MoeLoader |
2021-07-22T20:47:41Z |
| 90 |
Ling-V2 |
245 |
18 |
Python |
4 |
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI. |
2025-10-04T06:15:38Z |
| 91 |
moeins |
242 |
70 |
PHP |
2 |
萌音影视 - 在线影视应用 |
2018-10-31T01:47:27Z |
| 92 |
Ling |
237 |
20 |
Python |
2 |
Ling is a MoE LLM provided and open-sourced by InclusionAI. |
2025-05-14T06:34:57Z |
| 93 |
gdx-pay |
235 |
86 |
Java |
7 |
A libGDX cross-platform API for InApp purchasing. |
2025-10-10T06:47:44Z |
| 94 |
moebius |
231 |
4 |
PHP |
4 |
True coroutines for PHP>=8.1 without worrying about event loops and callbacks. |
2022-06-08T23:18:45Z |
| 95 |
ModuleFormer |
226 |
11 |
Python |
2 |
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. |
2025-09-18T00:30:52Z |
| 96 |
CoE |
226 |
28 |
Python |
3 |
Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models |
2025-11-04T14:49:21Z |
| 97 |
transformers-qwen3-moe-fused |
216 |
10 |
Python |
2 |
Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth |
2025-11-06T07:57:50Z |
| 98 |
LLaVA-MoD |
213 |
16 |
Python |
2 |
[ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation |
2025-03-31T09:41:38Z |
| 99 |
moe |
201 |
22 |
None |
1 |
Misspelling Oblivious Word Embeddings |
2019-08-06T12:42:31Z |
| 100 |
ComfyUI-WanMoeKSampler |
201 |
18 |
Python |
14 |
Modification of the KSampler for running models like Wan2.2 a14B |
2025-10-22T21:09:42Z |