mirror of
https://github.com/m5stack/StackFlow.git
synced 2026-05-20 11:32:11 -07:00
LittleMouse
331 B
331 B
benchmodulellm can be used to test llm unit inference performance
Only the llm unit definition files (model json) are required.
If no model specified, it would benchmark default list. More model networks may be added later.
Usage
python benchmodulellm.py --host 192.168.20.100 --port 10001 --test-items default.yaml