OpenSource/ollama

Autor	SHA1 Mensaxe	Data
Jesse Gross	0fbfcf3c9c model: Pass input tensor instead of raw data to models	hai 1 mes
Jesse Gross	0c220935bd input: Rename Options to Batch	hai 1 mes
Jeffrey Morgan	da0e345200 ml: use input context for extracting outputs (#9875)	hai 1 mes
Jesse Gross	282bfaaa95 ollamarunner: Use a separate context per multimodal input	hai 1 mes
Michael Yang	5e2e0b46b1 fix: error if image requested without vision model	hai 1 mes
Jesse Gross	a1cda80bcb model: Update encoder cache to use multimodal input processing handler	hai 1 mes
Michael Yang	7bae7fa5ce ml/backend/ggml: create tensor on specific backend	hai 2 meses
Jesse Gross	a7e63b82be ollamarunner: Improve multimodal input handling	hai 2 meses
Daniel Hiltgen	1fdb351c37 New engine: vision models and auto-fallback (#9113)	hai 2 meses
Jesse Gross	854a9195f3 attention: Remove unnecessary contiguous operations	hai 2 meses
Michael Yang	53d2990d9b model: add bos token if configured	hai 2 meses
Jesse Gross	5c5535c064 models: Prune unused outputs earlier in the forward pass	hai 2 meses
Jesse Gross	ed443a0393 Runner for Ollama engine	hai 4 meses
Jesse Gross	6945617af5 models: Move model into their own directory	hai 2 meses