OpenSource/ollama

Auteur	SHA1 Message	Date
Jesse Gross	0fbfcf3c9c model: Pass input tensor instead of raw data to models	il y a 1 mois
Jesse Gross	0c220935bd input: Rename Options to Batch	il y a 1 mois
Jeffrey Morgan	da0e345200 ml: use input context for extracting outputs (#9875)	il y a 1 mois
Patrick Devine	5f74d1fd47 gemma2 impl	il y a 2 mois
Jesse Gross	a1cda80bcb model: Update encoder cache to use multimodal input processing handler	il y a 1 mois
Michael Yang	7bae7fa5ce ml/backend/ggml: create tensor on specific backend	il y a 2 mois
Michael Yang	bab6f34dc0 ml/backend/ggml: update model loading for hybrid/multi backends	il y a 2 mois
Daniel Hiltgen	1fdb351c37 New engine: vision models and auto-fallback (#9113)	il y a 2 mois
Jesse Gross	854a9195f3 attention: Remove unnecessary contiguous operations	il y a 2 mois
Michael Yang	53d2990d9b model: add bos token if configured	il y a 2 mois
Jesse Gross	f53f4198c3 ml: Abstract attention out of model definitions	il y a 2 mois
Jesse Gross	5c5535c064 models: Prune unused outputs earlier in the forward pass	il y a 2 mois
Jesse Gross	ed443a0393 Runner for Ollama engine	il y a 4 mois
Jesse Gross	6945617af5 models: Move model into their own directory	il y a 2 mois