FlexGen

FlexGen is a high-throughput generation engine for running large language models with limited GPU memory (e.g., a 16GB T4 GPU or a 24GB RTX3090 gaming card!). This is a research project developed by HazyResearch@Stanford, SkyComputing@UC Berkeley, DS3Lab@ETH Zurich, CRFM@Stanford, and TogetherCompute. More: https://github.com/FMInference/FlexGen

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

This work presents Kornia – an open source computervision library which consists of a set of differentiable rou-tines and modules to solve generic computer vision prob-lems. The package uses PyTorch as its main backend bothfor efficiency and to take advantage of the reverse-modeauto-differentiation to define and compute the gradient ofcomplex functions. Inspired by OpenCV, Kornia … Lanjutkan membaca Kornia: an Open Source Differentiable Computer Vision Library for PyTorch