mirror of
https://github.com/ollama/ollama.git
synced 2025-03-17 21:32:14 +01:00
282bfaaa95
Currently there is a single context per sequence, shared all by all multimodal inputs. Since we build a vision encoder graph per image, with a large number of inputs we can eventually hit the maximum number of graph nodes per context. This changes to use a separate context for each image, ensuring that available resource limits are consistent.
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