Stars
All the source code for "Robot Learning: A Tutorial". Get involved to be featured in the next iteration!
An approach called model fusion which fuses multiple task-specific DNNs that are pre-trained separately and can have heterogeneous architectures into a single multi-task model, to accelerate the in…
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Master the fundamentals of machine learning, deep learning, and mathematical optimization by building key concepts and models from scratch using Python.
🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSy…
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
links to conference publications in graph-based deep learning
Artifact for PPoPP20 "Understanding and Bridging the Gaps in Current GNN Performance Optimizations"
A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.
[MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration
A curated list of neural network pruning resources.
Benchmarking Deep Learning operations on different hardware
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
An implementation of a deep learning recommendation model (DLRM)
A high performance and generic framework for distributed DNN training
Must-read papers on graph neural networks (GNN)
Reference models and tools for Cloud TPUs.
Automatically exported from code.google.com/p/sequitur
Differentiable architecture search for convolutional and recurrent networks
A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.
A complete computer science study plan to become a software engineer.
Example for applying Gaussian and Laplace clipping on activations of CNN.