OpenSource/ollama

Auteur	SHA1 Message	Date
Michael Yang	05a01fdecb ml/backend/ggml: consolidate system info logging	il y a 2 mois
Jesse Gross	21aa666a1e ml: Enable support for flash attention	il y a 2 mois
Jesse Gross	ee141cc821 ml: Empty tensor constructor for tensors	il y a 2 mois
Jesse Gross	854a9195f3 attention: Remove unnecessary contiguous operations	il y a 2 mois
Michael Yang	3e8b8a1933 ml: update Context.Forward interface	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	bd6a7d5e64 ollamarunner: Pass runner performance parameters to backends	il y a 2 mois
Daniel Hiltgen	df2680b4b9 Wire up system info log for new engine (#9123)	il y a 2 mois
Jesse Gross	ed443a0393 Runner for Ollama engine	il y a 4 mois
Jesse Gross	d773b7d671 backend: API to support full precision matmul	il y a 2 mois
Jesse Gross	4d4463b2bd backend: Support graph computation that does not return an output	il y a 2 mois
Jesse Gross	0e38297f87 backend: Consistently use int (vs. int64) for tensor shapes	il y a 2 mois
Jesse Gross	7e13f568dc backend: Don't return an error on Close	il y a 2 mois
Michael Yang	58245413f4 next ollama runner (#7913)	il y a 2 mois