Show HN: Flide: Make Jev-like decision models up to 9.5x faster
Flide is a fast inference infrastructure for Jev-style decision models that achieves up to 9.5x faster performance than vLLM and SGLang through exact state forking technology. The system serves multiple decision model families and provides a /v1/systemone API for making decisions with multiple options. Flide is available on PyPI and supports numerous pre-configured models that can be deployed with simple command-line commands.