RDMA core userspace libraries and daemons

Yinghan's Code Sample

Yet another PyTorch implementation of Stable Diffusion (probably easy to read)

Infiniband Verbs Performance Tests

cuDTW++: Ultra-Fast Dynamic Time Warping on CUDA-enabled GPUs

kaldi-asr/kaldi is the official location of the Kaldi project.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Implement Flash Attention using Cute.

Web UI for AIOS: AIOS AgentHub and AIOS AgentChat

FlagPerf is an open-source software platform for benchmarking AI chips.

FlagGems is an operator library for large language models implemented in Triton Language.

TransferBench is a utility capable of benchmarking simultaneous copies between user-specified devices (CPUs/GPUs)

本书为《C++17 the complete guide》的个人中文翻译，仅供学习和交流使用，侵删

VPTQ, A Flexible and Extreme low-bit quantization algorithm

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA

[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Qwen / DeepSeek), Knowledge Base (file upload / knowledge managemen…

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

一个基于C++11的轻量级网络框架，基于线程池技术可以实现大并发网络IO

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

SGLang is a fast serving framework for large language models and vision language models.

Dynamic Memory Management for Serving LLMs without PagedAttention

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

CUDA Core Compute Libraries

🤖一个基于 WeChaty 结合 OpenAi ChatGPT / Kimi / 讯飞等Ai服务实现的微信机器人 ，可以用来帮助你自动回复微信消息，或者管理微信群/好友，检测僵尸粉等...

A simple prompt-chatting AI based on wechaty and fintuned NLP model