OpenSource/ollama

Autor	SHA1 Nachricht	Datum
Jesse Gross	e5bcc51ae1 ggml-backend: Don't recreate the scheduler for each context	vor 2 Monaten
Jesse Gross	bd6a7d5e64 ollamarunner: Pass runner performance parameters to backends	vor 2 Monaten
Daniel Hiltgen	df2680b4b9 Wire up system info log for new engine (#9123)	vor 2 Monaten
Jesse Gross	ed443a0393 Runner for Ollama engine	vor 4 Monaten
Jesse Gross	d223f3b697 ggml-backend: Close on nil should be a no-op	vor 3 Monaten
Jesse Gross	60830695c2 ggml-backend: Ensure data is available after async computation	vor 3 Monaten
Jesse Gross	01d9a46854 ggml-backend: Let GGML allocate context memory	vor 3 Monaten
Jesse Gross	d773b7d671 backend: API to support full precision matmul	vor 2 Monaten
Jesse Gross	4d4463b2bd backend: Support graph computation that does not return an output	vor 3 Monaten
Jesse Gross	0e38297f87 backend: Consistently use int (vs. int64) for tensor shapes	vor 3 Monaten
Jesse Gross	7e13f568dc backend: Don't return an error on Close	vor 3 Monaten
Michael Yang	58245413f4 next ollama runner (#7913)	vor 2 Monaten