DeepSpeed Compression: A composable library for extreme

Large-scale models are revolutionizing deep learning and AI research, driving major improvements in language understanding, generating creative texts, multi-lingual translation and many more. But despite their remarkable capabilities, the models’ large size creates latency and cost constraints that hinder the deployment of applications on top of them. In particular, increased inference time and memory consumption […]

DeepSpeed - Microsoft Research: Timeline

ChatGPT只是前菜，2023要来更大的！ - 墨天轮

Microsoft's Open Sourced a New Library for Extreme Compression of Deep Learning Models, by Jesus Rodriguez

GitHub - microsoft/DeepSpeed: DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

This AI newsletter is all you need #6 – Towards AI

ZeroQuant与SmoothQuant量化总结-CSDN博客

PDF) DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing

Optimization approaches for Transformers [Part 2]

PDF] DeepSpeed- Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale

GitHub - microsoft/DeepSpeed: DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepSpeed Compression: A composable library for extreme compression and zero-cost quantization - Microsoft Research

GitHub - samuelcolvin/pydantic-testing-DeepSpeed: See

GitHub - microsoft/DeepSpeed: DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.