minicpm5-deploy

name	minicpm5-deploy
description	Pick the right inference backend for a MiniCPM5-1B checkpoint and route to a backend-specific cookbook skill. Use when the user wants to deploy / serve / chat-with / benchmark a MiniCPM5 model and has not yet committed to a specific engine, or when they say "deploy MiniCPM5", "run MiniCPM5", "serve MiniCPM5", "MiniCPM5 推理", "部署 MiniCPM5".

Deploy MiniCPM5-1B — backend router

You're being asked to deploy / serve / chat-with a MiniCPM5-1B checkpoint. Your job is to pick exactly one backend skill below based on the user's hardware, format, and goal, then invoke that skill rather than improvising.

1. Required input from the user

Before picking a backend, you MUST know:

Variable	Example	Where to ask
MODEL_PATH	HF id openbmb/MiniCPM5-1B (post-release) or a local path	"Which checkpoint? HF id or local path?"
Hardware	NVIDIA GPU / Apple Silicon / CPU only	infer from context, otherwise ask
Goal	"interactive chat" / "OpenAI server" / "Python script" / "benchmark"	infer from context

Available checkpoints on Hugging Face

Variant	HF repo	Use with
HF fp16 (recommended)	openbmb/MiniCPM5-1B	transformers / vllm (no --quantization) / sglang / any minicpm5-finetune-*