smvorwerk/xlstm-cuda

Cuda implementation of Extended Long Short Term Memory (xLSTM) with C++ and PyTorch ports

32
/ 100
Emerging

This is a specialized library for machine learning researchers and practitioners working with sequence data. It allows you to build models that process inputs like time series data or text, producing predictions or generated sequences that capture complex temporal relationships. Researchers in AI and deep learning who are experienced with neural network architectures would use this.

No commits in the last 6 months.

Use this if you are developing advanced deep learning models for tasks like time series forecasting or natural language generation and need an LSTM variant that handles long-term dependencies more effectively.

Not ideal if you are looking for a plug-and-play solution without deep knowledge of neural network architecture, or if you do not have access to CUDA-enabled hardware.

deep-learning-research natural-language-processing time-series-forecasting neural-networks generative-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

91

Forks

12

Language

C++

License

Last pushed

Jun 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/smvorwerk/xlstm-cuda"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.