AI inference deployment toolkit. Build deployment configurations with live validation, generate CLI commands, and explore the full configuration schema.
Interactive YAML editor for FlexInfer deployment configurations. Build, validate with live schema checking, and export configurations for deployment testing.
Pick one of the flexinfer CLI commands, fill in its arguments and flags, and copy the command line. Commands, flags, and defaults are transcribed from the CLI source.
FlexInfer is an AI inference orchestration platform for Kubernetes. It simplifies deploying and scaling large language models with support for multiple backends, GPU allocation, and schema-checked configurations.
Set up your first FlexInfer deployment. Install, configure, and deploy your first model.
Complete reference for flexinfer-config.yaml with all options and examples.
How backend plugins choose images, ports, args, and probes per GPU vendor for vLLM, MLC-LLM, llama.cpp, Ollama, and the image backends.
Production deployment, scaling, monitoring, and troubleshooting.
The CLI builder is transcribed from the CLI source, and the config editor checks the flexinfer-config schema written for this playground. Neither touches a cluster: check permissions, runtime support, and capacity in your own environment.