OpenSource/ollama

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