Download
Hummingbird is a library for compiling trained traditional ML models into tensor computations. Hummingbird allows users to seamlessly leverage neural network frameworks (such as PyTorch) to accelerate traditional ML models. Thanks to Hummingbird, users can benefit from (1) all the current and future optimizations implemented in neural network frameworks; (2) native hardware acceleration; (3) having a unique platform to support both traditional and neural network models; and having all of this (4) without having to re-engineer their models.
Features
- Hummingbird works by reconfiguring algorithmic operators
- Documentation available
- Examples available
- Once PyTorch is installed, you can get Hummingbird from pip
- Hummingbird was tested on Python 3.9, 3.10 and 3.11
- For Linux, Windows and MacOS
Project Samples
Categories
Machine LearningLicense
MIT LicenseFollow Hummingbird
Other Useful Business Software
CloudZero: The Cloud Cost Optimization Platform
CloudZero is the leader in proactive cloud cost efficiency. We enable engineers to build cost-efficient software without slowing down innovation. CloudZero's next-generation cloud cost optimization platform automates the collection, allocation, and analysis of cloud costs to uncover savings opportunities and improve unit economics. We are the only platform that enables companies to understand 100% of their operational cloud spend and take an engineering-led approach to optimizing that spend. CloudZero is used by industry leaders worldwide, such as Coinbase, Klaviyo, Miro, Nubank, and Rapid7.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Hummingbird!
