Jesse Gross aba1575315 llm: Don't try to load split vision models in the Ollama engine ... If a model with a split vision projector is loaded in the Ollama engine, the projector will be ignored and the model will hallucinate a response. Instead, fallback and try to load the model in the llama engine.		2025-09-11 11:41:55 -07:00
..
llm_darwin.go	Optimize container images for startup (#6547)	2024-09-12 12:10:30 -07:00
llm_linux.go	Optimize container images for startup (#6547)	2024-09-12 12:10:30 -07:00
llm_windows.go	win: lint fix (#10571)	2025-05-05 11:08:12 -07:00
memory_test.go	llm: New memory management	2025-08-14 15:24:01 -07:00
memory.go	llm: Remove unneeded warning with flash attention enabled	2025-09-10 16:40:45 -07:00
server_test.go	llm: New memory management	2025-08-14 15:24:01 -07:00
server.go	llm: Don't try to load split vision models in the Ollama engine	2025-09-11 11:41:55 -07:00
status.go	Improve crash reporting (#7728)	2024-11-19 16:26:57 -08:00