Jesse Gross 282bfaaa95 ollamarunner: Use a separate context per multimodal input ... 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.		2025-03-14 15:38:54 -07:00
..
cache.go	llm: remove internal subprocess req and resp types (#9324)	2025-03-14 15:21:53 -07:00
cache_test.go	model: Update encoder cache to use multimodal input processing handler	2025-03-09 17:05:26 -07:00
runner.go	ollamarunner: Use a separate context per multimodal input	2025-03-14 15:38:54 -07:00