Production-grade Turborepo template for Next.js apps.

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Open-source observability for your LLM application, based on OpenTelemetry

Python scripts performing Metric Monocular Depth Estimation using the Unidepth model in ONNX.

Distributed LLM and StableDiffusion inference for mobile, desktop and server.

A lightweight library for portable low-level GPU computation using WebGPU.

小彭老师领衔编写，现代C++的中文百科全书

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

Container to WASM converter

LLM Zoomcamp - a free online course about building a Q&A system

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

Windows inside a Docker container.

PhotoMaker [CVPR 2024]

Deep learning in Rust, with shape checked tensors and neural networks

Build, bundle & ship your Rust WASM application to the web.

Minimalist ML framework for Rust

Python packaging and dependency management made easy

《AI 研发提效：自己动手训练 LoRA》，包含 Llama （Alpaca LoRA）模型、ChatGLM （ChatGLM Tuning）相关 Lora 的训练。训练内容：用户故事生成、测试代码生成、代码辅助生成、文本转 SQL、文本生成代码……

peer-2-peer that just works

a FUSE file system based on Google Drive

The Google Drive/OneDrive/etc alternative using Telegram API

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

Android 技术中台，但愿人长久，搬砖不再有

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

📝 An Awesome Collection of Chinese Legal Dataset and Relevant Resources. 致力于收集全面的中文法律数据源

Python bindings for the Transformer models implemented in C/C++ using GGML library.

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Universal LLM Deployment Engine with ML Compilation