lmnt-com/haste
Haste: a fast, simple, and open RNN library
This project provides highly optimized building blocks for deep learning models that process sequential data like audio, text, or sensor readings. It allows machine learning engineers and researchers to quickly integrate state-of-the-art recurrent neural network (RNN) layers into their TensorFlow or PyTorch projects. You provide your sequential data, and the layers output processed representations, enabling faster development of high-performance models for tasks like speech recognition or natural language understanding.
336 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher developing models that rely on recurrent neural networks (RNNs) and need to maximize their performance and efficiency on NVIDIA GPUs.
Not ideal if you are new to deep learning or only require basic RNN functionality without advanced performance tuning or GPU acceleration.
Stars
336
Forks
31
Language
C++
License
Apache-2.0
Category
Last pushed
Jul 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lmnt-com/haste"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
flashlight/flashlight
A C++ standalone library for machine learning
NVlabs/tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
KasperskyLab/knp
Kaspersky Neuromorphic Platform
wichtounet/dll
Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)