DeepSpeed: Accelerating large-scale model inference and training

miro.medium.com/v2/resize:fit:1400/0*7l0yGZjkm3dyx

miro.medium.com/v2/resize:fit:1400/1*DafLIAEn1yQAx

2201.05596] DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale

Machine Learning and Inference Laboratory - Photos from Conferences, thomas mitchell machine learning

N] Improvement on model's inference from DeepSpeed team. [D] How

GitHub - Naagar/a_paper_a_day: I am trying a new initiative - a paper a day. This repository will hold all those papers and related summaries and notes.

GitHub - microsoft/DeepSpeed: DeepSpeed is a deep learning

Samyam Rajbhandari (@samyamrb) / X

Toward INT8 Inference: Deploying Quantization-Aware Trained

LLM Inference Unveiled: Survey and Roofline Model Insights

DeepSpeed ZeRO++: A leap in speed for LLM and chat model training

SpecInfer: Accelerating Generative LLM Serving with Speculative