llm --help

Let's help help help devs.

Target: <1000ms. Several important LLM CLI tools take multiple seconds. PRs welcome ❤️

Run: Jun 14, 2026 10:08 UTC / CPU: AMD Ryzen 7 8700F 8-Core Processor; GPU: 1x RTX 5060 Ti

tool cold warm version
tensorrt-llm --help18086ms9115ms1.2.1
vllm --help12179ms5326ms0.23.0
sglang --help9732ms3566ms0.5.9
VLMEvalKit --help9289ms3238msv0.2
transformers --help7141ms1897ms5.12.0
datasets --help1880ms571ms5.0.0
llm --help698ms327ms0.31
openai --help557ms282ms2.34.0
hf --help540ms212ms1.19.0
lm-eval --help968ms183ms0.4.12
langchain-cli --help431ms151ms0.0.37
tokenspeed --help274ms115ms0.1.0@9d63ac6
ollama --help12ms10ms0.30.8
llama.cpp --help18ms9msb9630