mirror of
https://github.com/ollama/ollama.git
synced 2025-03-18 22:01:47 +01:00
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.