OAID/AutoKernel
AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。
Building and deploying deep learning models often means slow performance on different hardware. This tool helps optimize the fundamental operations (kernels) within neural networks, automatically generating high-performance, low-level code for various hardware like CPUs, GPUs, and specialized accelerators. It's for embedded systems engineers or AI deployment specialists who need to get deep learning models running as fast as possible on target devices.
743 stars. No commits in the last 6 months.
Use this if you need to significantly improve the execution speed of deep learning algorithms on diverse hardware platforms without manually writing complex, low-level optimization code.
Not ideal if you are a data scientist primarily focused on model training and experimentation, and are not concerned with model deployment performance on specific hardware.
Stars
743
Forks
82
Language
C++
License
Apache-2.0
Category
Last pushed
Sep 23, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/OAID/AutoKernel"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
process-intelligence-solutions/pm4py
Official public repository for PM4Py (Process Mining for Python) — an open-source library for...
autogluon/autogluon
Fast and Accurate ML in 3 Lines of Code
microsoft/FLAML
A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
shankarpandala/lazypredict
Lazy Predict help build a lot of basic models without much code and helps understand which...
alteryx/evalml
EvalML is an AutoML library written in python.