Tag: #strict
Kubernetes, DevOps and MLOps, written from things we ran and measured ourselves · 1 posts
Tool Calling: The parser turns text into function calls, and strict binds the arguments
When a model calls a tool, it is actually writing text in a predefined format. vLLM injects a list of tools into the prompt using a chat template, and a parser converts the text written by the model into OpenAI-format to
2026-10-27 · 15 min read #vLLM#도구 호출#tool calling#function calling#구조화 출력