Albero (Tree): v0.6.3-rc0

Michael Yang 74bd09652d ml/backend/ggml: load tensors in 32KiB chunks		1 mese fa
..
common	ed443a0393 Runner for Ollama engine	2 mesi fa
llamarunner	3892c3a703 llm: remove internal subprocess req and resp types (#9324)	1 mese fa
ollamarunner	74bd09652d ml/backend/ggml: load tensors in 32KiB chunks	1 mese fa
README.md	ed443a0393 Runner for Ollama engine	2 mesi fa
runner.go	ed443a0393 Runner for Ollama engine	2 mesi fa

`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

runner