Apache TVM

About Apache TVM

The vision of the Apache TVM Project is to host a diverse community of experts and practitioners in machine learning, compilers, and systems architecture to build an accessible, extensible, and automated open-source framework that optimizes current and emerging machine learning models for any hardware platform. TVM provides the following main features:

Compilation of deep learning models into minimum deployable modules. Infrastructure to automatic generate and optimize models on more backend with better performance.

Key Features & Capabilities

Performance

Compilation and minimal runtimes commonly unlock ML workloads on existing hardware.

Run Everywhere

CPUs, GPUs, browsers, microcontrollers, FPGAs and more.

Automatically generate and optimize tensor operators on more backends.

Flexibility

Need support for block sparsity, quantization (1,2,4,8 bit integers, posit), random forests/classical ML, memory planning, MISRA-C compatibility, Python prototyping or all of the above?

TVM’s flexible design enables all of these things and more.

Ease of Use

Compilation of deep learning models in Keras, MXNet, PyTorch, Tensorflow, CoreML, DarkNet and more. Start using TVM with Python today, build out production stacks using C++, Rust, or Java the next day.

Docs

Written with care & love for you.

Join the TVM community

Blog

Read more about TVM and our thinking

网址：Apache TVM https://mxgxt.com/news/view/1670802

相关内容

Apache Doris、DorisDB与StarRocks：揭秘背后的故事与关系
Apache Tomcat/7.0.11
StarRocks 昨日回应：关于 StarRocks 相关疑问的解答
selectdb和starrocks是什么关系?
「AI Infra 工程师（web3 明星创业公司招聘」
揭秘Kubernetes：揭秘容器编排界的明星与竞争对手的较量
“明星售点”活动开始前需要回传内容（）
AutoConfiguration
网络数据分析工具有哪些?
八大中间件介绍以及漏洞分析

随便看看