A cross-platform private song playback service.

verl: Volcano Engine Reinforcement Learning for LLMs

一个 Openwrt 标准的软件中心，纯脚本实现，只依赖Openwrt标准组件。支持其它固件开发者集成到自己的固件里面。更方便入门用户搜索安装插件。The iStore is a app store for OpenWRT

Microsoft Collective Communication Library

A simple, performant and scalable Jax LLM!

GLake: optimizing GPU memory management and IO transmission.

PyTorch bindings for CUTLASS grouped GEMM.

Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Microsoft Automatic Mixed Precision Library

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

PX4 Autopilot Software

Get protein embeddings from protein sequences

SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

CUDA Templates for Linear Algebra Subroutines

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilizatio…

A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")

PyTorch extensions for high performance and large scale training.

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

This is the notes of the way of machine learning study. You may find something useful in it.

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

Inference code for Llama models

Efficient Training (including pre-training and fine-tuning) for Big Models

An open-source user mode debugger for Windows. Optimized for reverse engineering and malware analysis.

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Free and Open Source Reverse Engineering Platform powered by rizin

闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题