OpenSource/ollama

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