Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
xtuner
AI repositoriesA Next-Generation Training Engine Built for Ultra-Large MoE Models
git clone https://github.com/InternLM/xtuner.git -
LlamaFactory
AI repositoriesUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
git clone https://github.com/hiyouga/LlamaFactory.git -
vllm
AI repositoriesA high-throughput and memory-efficient inference and serving engine for LLMs
git clone https://github.com/vllm-project/vllm.git -
GLM-4.5
AI repositoriesGLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
git clone https://github.com/zai-org/GLM-4.5.git -
sglang
AI repositoriesSGLang is a high-performance serving framework for large language models and multimodal models.
git clone https://github.com/sgl-project/sglang.git -
project-maya
AI repositoriesProject Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
git clone https://github.com/mw00/project-maya.git -
BigMoeOnEdge
AI repositoriesRun MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
git clone https://github.com/Helldez/BigMoeOnEdge.git -
SwiftLM
AI repositories⚡ 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.
git clone https://github.com/SharpAI/SwiftLM.git -
llm-architecture-from-scratch
AI repositoriesImplementing LLM architectures from scratch in PyTorch
git clone https://github.com/YeonwooSung/llm-architecture-from-scratch.git -
diy-llm
AI repositoriesCovers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer、MoE、分布式训练、缩放定律、推理与对齐,6 项渐进代码作业,掌握 LLM 全栈知识
git clone https://github.com/datawhalechina/diy-llm.git -
ms-swift
AI repositoriesUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 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).
git clone https://github.com/modelscope/ms-swift.git -
uccl
AI repositoriesUCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
git clone https://github.com/uccl-project/uccl.git -
kimi-k3-in-c
AI repositoriesA 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.
git clone https://github.com/FareedKhan-dev/kimi-k3-in-c.git -
pegainfer
AI repositoriesPure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
git clone https://github.com/pegainfer-project/pegainfer.git -
inferssd
AI repositoriesRun models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
git clone https://github.com/wici-ai/inferssd.git -
janas
AI repositories37 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.
git clone https://github.com/prabanta-dev/janas.git -
ARIS-in-AI-Offer
AI repositoriesBilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱
git clone https://github.com/wanshuiyin/ARIS-in-AI-Offer.git -
slotstream
AI repositoriesRun a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 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.
git clone https://github.com/carloslfu/slotstream.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.