Wavenet Autoencoder for Unsupervised speech representation learning (after Chorowski, Jan 2019)

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

CUDA Templates and Python DSLs for High-Performance Linear Algebra

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

Fast Inference Solutions for BLOOM

Making large AI models cheaper, faster and more accessible

Large Language Model Text Generation Inference

The simplest way to run LLaMA on your local machine

LLM inference in C/C++

C++ implementation for BLOOM

Running large language models on a single GPU for throughput-oriented scenarios.

Accessible large language models via k-bit quantization for PyTorch.

🙃 A delightful community-driven (with 2,400+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python…

a library for audio and music analysis

A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems", which is `dmls-book`

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

C++那些事

Interview questions to ponder related to computer vision.

CV算法岗知识点及面试问答汇总，主要分为计算机视觉、机器学习、图像处理和 C++基础四大块，一起努力向offers发起冲击！

根据网易云音乐的歌单, 下载flac无损音乐到本地. Download the FLAC music from Internet according to your NeteaseCloudMusic playlist.

《Linux高性能服务器编程》上的例子

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

AutoML tools chain

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

Boosting your Web Services of Deep Learning Applications.

Tensorflow implementation of S4L: Self-Supervised Semi-Supervised Learning

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.