Git Stars Git Stars

#moe Repositories

Discover 34 active open source GitHub repositories tagged with #moe, accumulating 317,125 total stars (averaging 9,327 stars per project). Leading this topic is vllm-project/vllm with 97,302 stars.

34
Total Repositories
317,125
Total Stars
9,327
Avg Stars/Repo
1
vllm-project/vllm

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

vllm-project
โญ 97,302 Python ๐Ÿ‘ค vllm-project Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-02-09
2
hiyouga/LlamaFactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

hiyouga
โญ 76,171 Python ๐Ÿ‘ค hiyouga User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-05-28
3
sgl-project/sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

sgl-project
โญ 38,899 Python ๐Ÿ‘ค sgl-project Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2024-01-08
4
FlashML-org/FreeToken

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

FlashML-org
โญ 17,522 Python ๐Ÿ‘ค FlashML-org User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-07-20
5
modelscope/ms-swift

Use PEFT or full-parameter training for CPT/SFT/DPO/GRPO on 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, LLaVA, Phi4, ...) (AAAI 2025).

modelscope
โญ 16,138 Python ๐Ÿ‘ค modelscope Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-08-01
6
NVIDIA/TensorRT-LLM

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.

NVIDIA
โญ 15,112 Python ๐Ÿ‘ค NVIDIA Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-08-16
7
FareedKhan-dev/kimi-k3-in-c

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

FareedKhan-dev
โญ 12,523 C ๐Ÿ‘ค FareedKhan-dev User ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2026-08-01
8
flashinfer-ai/flashinfer

FlashInfer: Kernel Library for LLM Serving

flashinfer-ai
โญ 6,982 Cuda ๐Ÿ‘ค flashinfer-ai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-07-22
9
czy0729/Bangumi

:electron: An unofficial https://bgm.tv UI-first app client for Android and iOS, built with React Native. An ad-free, hobby-driven, non-profit, ACG-focused alternative to Douban for anime tracking, a third-party bgm.tv client. Redesigned for mobile devices, featuring many enhanced functionalities hard to implement on the web version, along with substantial customization options. Currently adapted for iOS / Android.

czy0729
โญ 6,268 TypeScript ๐Ÿ‘ค czy0729 User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2019-05-08
10
zai-org/GLM-4.5

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

zai-org
โญ 4,426 Python ๐Ÿ‘ค zai-org Organization ๐Ÿ• Updated 2026-02-01 ๐Ÿ“… Created 2025-07-20
11
mw00/project-maya

Run GLM-5.3 (744B), DeepSeek-V4.1-Flash (748B), MiniMax-M3.1-Flash (428B), GLM-5.3-Flash (321B), and Hy4-Flash (220B) on your own GPUs โ€” starting from 8 GB of VRAM, with NVIDIA and AMD support, one dashboard, and an OpenAI- and Anthropic-compatible API.

mw00
โญ 3,140 C++ ๐Ÿ‘ค mw00 User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-10-06
12
PKU-YuanGroup/MoE-LLaVA

ใ€TMM 2025๐Ÿ”ฅใ€‘ Mixture-of-Experts for Large Vision-Language Models

PKU-YuanGroup
โญ 2,321 Python ๐Ÿ‘ค PKU-YuanGroup Organization ๐Ÿ• Updated 2025-07-15 ๐Ÿ“… Created 2023-12-14
13
MoonshotAI/MoBA

MoBA: Mixture of Block Attention for Long-Context LLMs

MoonshotAI
โญ 2,122 Python ๐Ÿ‘ค MoonshotAI Organization ๐Ÿ• Updated 2025-04-03 ๐Ÿ“… Created 2025-02-17
14
uccl-project/uccl

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

uccl-project
โญ 1,590 C++ ๐Ÿ‘ค uccl-project Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-01-06
15
wici-ai/inferssd

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

wici-ai
โญ 1,277 C++ ๐Ÿ‘ค wici-ai Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-10-22
16
davidmrau/mixture-of-experts

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

davidmrau
โญ 1,215 Python ๐Ÿ‘ค davidmrau User ๐Ÿ• Updated 2024-04-19 ๐Ÿ“… Created 2019-07-19
17
Helldez/BigMoeOnEdge

Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, or edge device. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.

Helldez
โญ 1,066 C++ ๐Ÿ‘ค Helldez User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-07-10
18
microsoft/Tutel

Tutel MoE: Optimized Mixture-of-Experts Library, Supporting GLM/Kimi/GPT/DeepSeek/Qwen with FP8/NVFP4/MXFP4

microsoft
โญ 1,027 C ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2021-08-06
19
wangeai/K3Flight

Run Kimi K3 locally on CPU with ~55GB measured runtime RAM. A single-file Linux inference server powered by cPilot Runtime.

wangeai
โญ 1,019 HTML ๐Ÿ‘ค wangeai Organization ๐Ÿ• Updated 2026-07-31 ๐Ÿ“… Created 2026-07-30
20
NVIDIA/cudnn-frontend

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

NVIDIA
โญ 1,008 Cuda ๐Ÿ‘ค NVIDIA Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2021-01-22
21
pjlab-sys4nlp/llama-moe

โ›ท๏ธ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

pjlab-sys4nlp
โญ 1,004 Python ๐Ÿ‘ค pjlab-sys4nlp Organization ๐Ÿ• Updated 2024-12-06 ๐Ÿ“… Created 2023-07-24
22
whitecircle/halo

Halo is an open-source framework built by White Circle for training large language and multimodal models

whitecircle
โญ 868 Python ๐Ÿ‘ค whitecircle Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-08-26
23
sail-sg/Adan

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

sail-sg
โญ 818 Python ๐Ÿ‘ค sail-sg Organization ๐Ÿ• Updated 2025-06-08 ๐Ÿ“… Created 2022-09-01
24
ScienceOne-AI/DeepSeek-671B-SFT-Guide

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.

ScienceOne-AI
โญ 806 Python ๐Ÿ‘ค ScienceOne-AI User ๐Ÿ• Updated 2025-03-13 ๐Ÿ“… Created 2025-03-07
25
SharpAI/SwiftLM

โšก Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

SharpAI
โญ 802 Swift ๐Ÿ‘ค SharpAI Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-03-21
26
Tencent/YOLO-Master

[CVPR2026]๐Ÿš€๐Ÿš€๐Ÿš€Official code for the paper "YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection." *(YOLO = You Only Look Once)* ๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ

Tencent
โญ 790 Python ๐Ÿ‘ค Tencent Organization ๐Ÿ• Updated 2026-11-15 ๐Ÿ“… Created 2025-12-26
27
YeonwooSung/llm-architecture-from-scratch

Implementing LLM architectures from scratch in PyTorch

YeonwooSung
โญ 751 Python ๐Ÿ‘ค YeonwooSung User ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2026-09-16
28
pegainfer-project/pegainfer

Pure Rust + CUDA LLM inference engine โ€” no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

pegainfer-project
โญ 748 Rust ๐Ÿ‘ค pegainfer-project Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-02-17
29
prabanta-dev/janas

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.

prabanta-dev
โญ 738 C ๐Ÿ‘ค prabanta-dev Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-09-20
30
carloslfu/slotstream

Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16โ€“64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

carloslfu
โญ 674 Swift ๐Ÿ‘ค carloslfu User ๐Ÿ• Updated 2026-11-17 ๐Ÿ“… Created 2026-08-28
31
wanshuiyin/ARIS-in-AI-Offer

Bilingual (Chinese + English) ML / LLM / diffusion / agent interview cheat sheets for AI autumn recruiting โ€” generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML that can be read anywhere โ€” plus a CVโ†’DBLP fact-checked academic homepage generator and hand-authored long-form blogs ๐ŸŒฑ

wanshuiyin
โญ 661 Python ๐Ÿ‘ค wanshuiyin User ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-05-19
32
ymcui/Chinese-Mixtral

Chinese Mixtral Mixture-of-Experts LLMs (Chinese Mixtral MoE LLMs)

ymcui
โญ 613 Python ๐Ÿ‘ค ymcui User ๐Ÿ• Updated 2026-04-19 ๐Ÿ“… Created 2024-01-11
33
kacper-daftcode/vLLM-Moet

Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0

kacper-daftcode
โญ 580 Sass ๐Ÿ‘ค kacper-daftcode User ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-06-15
34
Indras-Mirror/Xolotl

Xolotl: run DeepSeek-V4.1-Flash, all 552B parameters, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s agent, ~41 fast, 512K context. Plus Inkling-2-Mini (Thinking Machines, own engine + MTP drafter), GLM-5.3-Flash, Qwen3.8, LFM3-Omni. MoE experts tiered across VRAM, RAM, and NVMe (Xolotl Direct). OpenAI + Anthropic API.

Indras-Mirror
โญ 549 C++ ๐Ÿ‘ค Indras-Mirror User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-10-06

Frequently Asked Questions

1

What is the most popular #moe repository on GitHub?

The top ranked open source #moe project on GitHub is vllm-project/vllm with 97,302 stars. A high-throughput and memory-efficient inference and serving engine for LLMs

2

Which programming languages are most used in #moe repositories?

Among the top ranked #moe projects on GitHub, the most common programming languages are Python, C++, C, Cuda.

3

How is the #moe repository ranking calculated?

We track 34 active open source repositories tagged with #moe (500+ stars), totaling 317,125 stars with an average of 9,327 stars per repository. Rankings update daily from the GitHub API.