Stars
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
Letta (formerly MemGPT) is a framework for creating LLM services with memory.
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Translate the video from one language to another and add dubbing. 将视频从一种语言翻译为另一种语言,同时支持语音识别转录、语音合成、字幕翻译。
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Ongoing research training transformer models at scale
The official GitHub page for the survey paper "A Survey of Large Language Models".
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Optimized primitives for collective multi-GPU communication
A V2Ray client for Android, support Xray core and v2fly core
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
a fast, scalable, multi-language and extensible build system
pip install nb_log 各种日志handler和自动转化项目的任意print的效果。日志自动彩色炫酷,可点击控制台的日志自动精确跳转到pycharm的文件和行号。文件日志多进程切割安全。在10个最重要方面全方位超过loguru
OpenMMLab Foundational Library for Training Deep Learning Models
Transformer related optimization, including BERT, GPT
Making large AI models cheaper, faster and more accessible
Kook.Net is an unofficial C# .NET implementation for KOOK API.