ribesstefano/Mapping-Multiple-LSTM-Models-on-FPGAs

Includes the SVD-based approximation algorithms for compressing deep learning models and the FPGA accelerators exploiting such approximation mechanism, as described in the paper Mapping multiple LSTM models on FPGAs.

37
/ 100
Emerging

This project helps hardware engineers and researchers working with Field-Programmable Gate Arrays (FPGAs) to efficiently run multiple deep learning models, specifically LSTMs. It takes pre-trained LSTM models and compresses them using an SVD-based approximation algorithm, then generates code for specialized FPGA hardware accelerators. The output is a highly optimized FPGA implementation capable of processing LSTM inferences much faster and with greater power efficiency.

No commits in the last 6 months.

Use this if you need to deploy several LSTM deep learning models onto FPGA hardware and require significant improvements in processing speed and resource utilization.

Not ideal if you are looking for a general-purpose deep learning deployment solution for CPUs or GPUs, or if you need to train new LSTM models.

FPGA development deep learning acceleration LSTM deployment hardware optimization embedded AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

16

Forks

4

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Mar 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ribesstefano/Mapping-Multiple-LSTM-Models-on-FPGAs"

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