baidu-research / catamount
Catamount is a compute graph analysis tool to load, construct, and modify deep learning models and to symbolically analyze their compute requirements
☆13Updated 3 years ago
Alternatives and similar repositories for catamount:
Users that are interested in catamount are comparing it to the libraries listed below
- Generating Families of Practical Fast Matrix Multiplication Algorithms☆12Updated 7 years ago
- ☆14Updated 6 years ago
- Code examples for CUDA and OpenACC☆34Updated 7 months ago
- Cairo lua bindings with extensions for torch☆15Updated 8 years ago
- ☆10Updated 2 years ago
- A runtime shape checker and auto-annotator for tensor programs (pronounced "stanley")☆39Updated 5 years ago
- An ONNX backend using PlaidML☆28Updated 6 years ago
- ☆15Updated 7 years ago
- Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing☆22Updated 6 months ago
- Distributed Learning by Pair-Wise Averaging☆53Updated 7 years ago
- stochs: fast stochastic solvers for machine learning in C++ and Cython☆26Updated 2 years ago
- Python bindings for libNVVM☆37Updated 10 years ago
- A very simple variant of adversarial training that yields excellent results on MNIST☆12Updated 9 years ago
- Python Binding to NVRTC☆79Updated 5 months ago
- Cephes Mathematical Functions library wrapped for Torch☆47Updated 9 years ago
- nGraph™ Backend for ONNX☆42Updated 2 years ago
- npcomp - An aspirational MLIR based numpy compiler☆51Updated 4 years ago
- ☆42Updated 5 years ago
- GPU Optimization and Memory Abstraction Framework☆32Updated 5 years ago
- The "CUDA templates" are a collection of C++ template classes and functions which provide a consistent interface to NVIDIA's "Compute Uni…☆27Updated 13 years ago
- Fork of magma to include more BLAS☆28Updated 8 years ago
- Examples of building probabilistic models with MXNet linear algebra operators☆23Updated 7 years ago
- GPU Automatically Tuned Linear Algebra Software☆28Updated 9 years ago
- A CUDA implementation of the PageRank Pipeline Benchmark☆32Updated 8 years ago
- A CUDA implementation of the Tsetlin Machine based on bitwise operators☆26Updated 5 years ago
- Scientific library for high-precision computations and research☆49Updated 7 years ago
- Torch7 bindings for cuda-convnet2 kernels!☆40Updated 8 years ago
- The Operator Vectorization Library, or OVL, is a python productivity library for defining high performance custom operators for the Tenso…☆68Updated 8 years ago
- Backprop training of recurrent neural networks with Hebbian plastic connections☆20Updated 3 years ago
- Improving spiking dynamical networks: Accurate delays, higher-order synapses, and time cells☆7Updated 7 years ago