InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. ms-swift

    AI repositories

    Use 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).

    Indexed GitHub, modelscope 16.1k ★Apache-2.0Updated 3 days ago

    git clone https://github.com/modelscope/ms-swift.git
  2. xtuner

    AI repositories

    A Next-Generation Training Engine Built for Ultra-Large MoE Models

    Stale GitHub, InternLM 5,221 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/InternLM/xtuner.git
  3. WhisperJAV

    AI repositories

    ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV

    Stale GitHub, meizhong986 2,394 ★MITUpdated 17 days ago

    git clone https://github.com/meizhong986/WhisperJAV.git
  4. GenieX

    AI repositories

    Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

    Stale GitHub, qualcomm 8,494 ★BSD-3-ClauseUpdated 11 days ago

    git clone https://github.com/qualcomm/GenieX.git
  5. vllm

    AI repositories

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

    Indexed GitHub, vllm-project 97.0k ★Apache-2.0Updated today

    git clone https://github.com/vllm-project/vllm.git
  6. LLM-TPU

    AI repositories

    Run generative AI models in sophgo BM1684X/BM1688

    Stale GitHub, sophgo 321 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/sophgo/LLM-TPU.git
  7. MaxKB

    AI repositories

    🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

    Indexed GitHub, 1Panel-dev 23.2k ★GPL-3.0Updated 2 days ago

    git clone https://github.com/1Panel-dev/MaxKB.git
  8. Automodel

    AI repositories

    🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

    Indexed GitHub, NVIDIA-NeMo 1,082 ★Apache-2.0Updated yesterday

    git clone https://github.com/NVIDIA-NeMo/Automodel.git
  9. LLaVA-OneVision-2

    AI repositories

    Fully Open Framework for Democratized Multimodal Training

    Stale GitHub, EvolvingLMMs-Lab 1,232 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-2.git
  10. deep-searcher

    AI repositories

    Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

    Stale GitHub, zilliztech 8,330 ★Apache-2.0Updated 55 days ago

    git clone https://github.com/zilliztech/deep-searcher.git
  11. Implementing LLM architectures from scratch in PyTorch

    Stale GitHub, YeonwooSung 856 ★BSD-3-ClauseUpdated 5 days ago

    git clone https://github.com/YeonwooSung/llm-architecture-from-scratch.git
  12. pegainfer

    AI repositories

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

    Stale GitHub, pegainfer-project 729 ★Apache-2.0Updated 18 days ago

    git clone https://github.com/pegainfer-project/pegainfer.git
  13. halogen-flash-server

    AI repositories

    Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

    Stale GitHub, peonist-ai 1,258 ★Custom licence (see repository)Updated 8 days ago

    git clone https://github.com/peonist-ai/halogen-flash-server.git
  14. janas

    AI repositories

    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.

    Indexed GitHub, prabanta-dev 717 ★GPL-3.0Updated today

    git clone https://github.com/prabanta-dev/janas.git
  15. unsloth

    AI repositories

    Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

    Indexed GitHub, unslothai 79.6k ★Apache-2.0Updated today

    git clone https://github.com/unslothai/unsloth.git
  16. slotstream

    AI repositories

    Run 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.

    Indexed GitHub, carloslfu 673 ★MITUpdated today

    git clone https://github.com/carloslfu/slotstream.git
  17. qwenputer

    AI repositories

    A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.

    Stale GitHub, divagr18 757 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/divagr18/qwenputer.git
  18. PolyStrata

    AI repositories

    Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.

    Stale GitHub, VecSzn 722 ★MITUpdated 16 days ago

    git clone https://github.com/VecSzn/PolyStrata.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.