litert-lm
Run and manage LiteRT-LM models. tldr-pages
On several platforms
Several platforms
List all imported models
litert-lm listIdentifyRun a local or imported model interactively
litert-lm run path/to/model.litertlmIdentifyRun a model directly from a Hugging Face repository with a single prompt
litert-lm run --from-huggingface-repo owner/repository model.litertlm --prompt "What is the capital of France?"IdentifyRun a model using GPU acceleration
litert-lm run path/to/model.litertlm --backend gpuIdentifyRun a multimodal model with an image attachment
litert-lm run path/to/model.litertlm --vision-backend gpu --attachment path/to/image.jpg --prompt "Describe this image."IdentifyRun a model with Python function calling tools via a preset file
litert-lm run path/to/model.litertlm --preset path/to/preset.pyIdentifyBenchmark a model's performance
litert-lm benchmark path/to/model.litertlmIdentifyStart an OpenAI-compatible API server on a specific port
litert-lm serve --port 9379Identify