neo-ai/neo-ai-dlr
Neo-AI-DLR is a common runtime for machine learning models compiled by AWS SageMaker Neo, TVM, or TreeLite.
This project provides a single, streamlined way to run your trained machine learning models on various hardware, including specialized devices, after they've been optimized by tools like AWS SageMaker Neo or TVM. It takes your pre-compiled model files as input and allows you to perform predictions quickly and efficiently. Machine learning engineers and developers deploying models to production environments would find this useful.
496 stars. No commits in the last 6 months.
Use this if you need to deploy and run machine learning models, especially deep learning or decision tree models, consistently across different hardware platforms and edge devices.
Not ideal if you are still in the model training or experimentation phase and have not yet compiled or optimized your models for deployment.
Stars
496
Forks
107
Language
C++
License
Apache-2.0
Category
Last pushed
May 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/neo-ai/neo-ai-dlr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
apache/tvm
Open Machine Learning Compiler Framework
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.