|
2 ヶ月 前 | |
---|---|---|
.. | ||
common | ed443a0393 Runner for Ollama engine | 2 ヶ月 前 |
llamarunner | 010313bb63 llamarunner: Init GGML before printing system info | 2 ヶ月 前 |
ollamarunner | bd6a7d5e64 ollamarunner: Pass runner performance parameters to backends | 2 ヶ月 前 |
README.md | ed443a0393 Runner for Ollama engine | 2 ヶ月 前 |
runner.go | ed443a0393 Runner for Ollama engine | 2 ヶ月 前 |
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>
curl -X POST -H "Content-Type: application/json" -d '{"prompt": "hi"}' http://localhost:8080/completion
curl -X POST -H "Content-Type: application/json" -d '{"prompt": "turn me into an embedding"}' http://localhost:8080/embedding