Important
BentoML is now part of Modular. Together, we're building a unified stack for high-performance AI inference.
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. It supports serving any model format/runtime and custom Python code, offering the key primitives for serving optimizations, task queues, batching, multi-model chains, distributed orchestration, and multi-GPU serving.
A collection of examples for BentoML, from deploying OpenAI-compatible LLM service, to building voice phone calling agents and RAG applications. Use these examples to learn how to use BentoML and build your own solutions.
Run any open-source LLMs (Llama, Mistral, Qwen, Phi and more) or custom fine-tuned models as OpenAI-compatible APIs with a single command. It features a built-in chat UI, state-of-the-art inference performance, and a simplified workflow for production-grade cloud deployment.
BentoCloud is the easist way to build and deploy with BentoML, in our cloud or yours. It brings fast and scalable inference infrastructure into any cloud, allowing AI teams to move 10x faster in building AI applications with ML/AI models, while reducing compute cost - by maxmizing compute utilization, fast GPU autoscaling, minimimal coldstarts and full observability. Sign up today!.
For end-to-end performance and portability across the AI execution stack, see Modular MAX.
Mojo is on the path to a stable 1.0 release in 2026, delivering semantic versioning and a high-performance language for CPU and GPU programming. As Mojo matures, BentoML will leverage Mojo's compiled performance for CPU and GPU kernels to push model inference performance even further. See the Mojo Roadmap for more information.
💬 Join the Modular Discord and Modular Forum
👀 Follow us on X @Modular and LinkedIn
📖 Read our blog
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
Configures opinionated GKE clusters
SGLang is a fast serving framework for large language models and vision language models.
CSI driver that uses a container image as a volume
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Scalable Visual-ChatGPT deployment on Kubernetes - Distributed multi-model inference graph powered by BentoML
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
Loading…