smvorwerk/xlstm-cuda
Cuda implementation of Extended Long Short Term Memory (xLSTM) with C++ and PyTorch ports
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.
Stars
91
Forks
12
Language
C++
License
—
Category
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.
Higher-rated alternatives
quic/efficient-transformers
This library empowers users to seamlessly port pretrained models and checkpoints on the...
ManuelSLemos/RabbitLLM
Run 70B+ LLMs on a single 4GB GPU — no quantization required.
alpa-projects/alpa
Training and serving large-scale neural networks with auto parallelization.
arm-education/Advanced-AI-Hardware-Software-Co-Design
Hands-on course materials for ML engineers to master extreme model quantization and on-device...
IST-DASLab/marlin
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes...