Jesse Gross 9679f40146 ml: Allow models to constrain inputs to a single batch 1 miesiąc temu
..
common ed443a0393 Runner for Ollama engine 2 miesięcy temu
llamarunner 3892c3a703 llm: remove internal subprocess req and resp types (#9324) 1 miesiąc temu
ollamarunner 9679f40146 ml: Allow models to constrain inputs to a single batch 1 miesiąc temu
README.md ed443a0393 Runner for Ollama engine 2 miesięcy temu
runner.go ed443a0393 Runner for Ollama engine 2 miesięcy temu

README.md

runner

Note: this is a work in progress

A minimial runner for loading a model and running inference via a http web server.

./runner -model <model binary>

Completion

curl -X POST -H "Content-Type: application/json" -d '{"prompt": "hi"}' http://localhost:8080/completion

Embeddings

curl -X POST -H "Content-Type: application/json" -d '{"prompt": "turn me into an embedding"}' http://localhost:8080/embedding