CMU-SPEED/SMaLLFramework
SMaLL: Software for rapidly instantiating Machine Learning Libraries
SMaLL helps embedded systems engineers quickly create machine learning inference libraries tailored for various edge device architectures. You provide your Deep Neural Network (DNN) model details and target hardware, and it generates an optimized, high-performance library for running the model on that specific device. This is ideal for developers building AI-powered features for resource-constrained hardware.
Use this if you need to deploy complex deep learning models on low-power, embedded devices and require optimized performance for different chip architectures.
Not ideal if you are working with cloud-based machine learning deployments or general-purpose computing where hardware-specific optimization for edge devices isn't a primary concern.
Stars
12
Forks
2
Language
C++
License
—
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CMU-SPEED/SMaLLFramework"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
davisking/dlib
A toolkit for making real world machine learning and data analysis applications in C++
ZigRazor/CXXGraph
Header-Only C++ Library for Graph Representation and Algorithms
apache/singa
a distributed deep learning platform
mlpack/mlpack
mlpack: a fast, header-only C++ machine learning library
hosseinmoein/DataFrame
C++ DataFrame for statistical, financial, and ML analysis in modern C++