Transformers with Arbitrarily Large Context

A minimal shared memory object store design

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

Supercharge Your Model Training

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Attempt at reproducing a SGNN's projection layer, but with word n-grams instead of skip-grams. Paper and more: https://aclweb.org/anthology/D18-1105

Preconditioned Conjugate Gradient in Pytorch

Mesh TensorFlow: Model Parallelism Made Easier

Code for the AAAI 2018 publication "SEE: Towards Semi-Supervised End-to-End Scene Text Recognition"

Learning What and Where to Draw

MXNet Model Serving

🔥🔥A MXNet implementation of DenseNet(with BC structure)🔥🔥

Notebooks for MXNet

Sparse matrix-matrix multiplication on CPU+GPU systems.

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

MPI for Torch

LowRankModels.jl is a julia package for modeling and fitting generalized low rank models.

The grand wiki