3
High-performance inference infrastructure for deploying and serving frontier AI models.
Open SourceInferenceModel Deployment
Back to startups
AI Infrastructure
BentoML
Open-source model serving and inference infrastructure for production AI systems.
Location
San Francisco, USA
Founded
2019
Founders
Chaoyu Yang
Views
2
GitHub forks
0
Open issues
0
License
—
Repository activity
—
About the company
BentoML provides an open-source framework for packaging, serving and deploying machine-learning models. It bridges model development and production infrastructure with reproducible services, adaptive batching, container deployment and cloud options for teams running modern inference workloads. Public product claims can change; confirm current capabilities, deployment requirements, pricing and support with the vendor.
Open SourceModel ServingInference
Verified data sources
Synced Aug 27, 2026Platform status: Active
Related startups
1.8K
3
An open-source, serverless cloud for AI inference, sandboxes and agents.
Open SourceServerless GPUAgent Sandboxes