hugot
Run ONNX transformer pipelines (like Hugging Face) natively in Go for inference and fine-tuning, with support for CPU, GPU, and TPU.
What is hugot?
Hugot is a Go library that allows developers to run ONNX transformer pipelines—such as those from Hugging Face—natively within Go applications. It solves the challenge of deploying AI models in Go production environments by providing seamless inference and fine-tuning capabilities without requiring external Python services.
Go developers and ML engineers who need to integrate transformer models (e.g., for NLP, computer vision) directly into their Go applications, especially those with performance or self-hosting requirements.
Hugot offers a performant, self-contained alternative to external API calls, enabling tight coupling of AI models with Go code, support for multiple hardware accelerators, and compatibility with Hugging Face's ecosystem.
Overview
Onnx transformer pipelines in Golang
Use Cases
Best For
- Deploying Hugging Face transformer models in Go microservices
- Running AI inference on-premises without external API dependencies
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
