hipersys-team/lightning
[SIGCOMM 2023] Lightning: A Reconfigurable Photonic-Electronic SmartNIC for Fast and Energy-Efficient Inference
This project offers a unique solution for quickly processing deep neural network inference requests using a specialized SmartNIC. It takes in real-time data packets needing inference and outputs the processed results much faster and with greater energy efficiency than traditional digital systems. Network engineers and data center operators who manage high-volume, real-time AI workloads will find this particularly useful.
No commits in the last 6 months.
Use this if you need to accelerate deep neural network inference directly on network traffic with exceptional speed and energy efficiency, bypassing common bottlenecks.
Not ideal if your primary goal is general-purpose data processing or if you do not operate with real-time, high-throughput AI inference demands at the network edge.
Stars
44
Forks
5
Language
Verilog
License
MIT
Category
Last pushed
Nov 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hipersys-team/lightning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
fastmachinelearning/hls4ml
Machine learning on FPGAs using HLS
alibaba/TinyNeuralNetwork
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
KULeuven-MICAS/zigzag
HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators
fastmachinelearning/hls4ml-tutorial
Tutorial notebooks for hls4ml
doonny/PipeCNN
An OpenCL-based FPGA Accelerator for Convolutional Neural Networks