OpenSource/ollama

Pembuat	SHA1 Pesan	Tanggal
Jesse Gross	854a9195f3 attention: Remove unnecessary contiguous operations	2 bulan lalu
Michael Yang	3e8b8a1933 ml: update Context.Forward interface	2 bulan lalu
Jesse Gross	f53f4198c3 ml: Abstract attention out of model definitions	2 bulan lalu
Michael Yang	2192a28eed ml/backend/ggml: fix rms norm	2 bulan lalu
Jesse Gross	e5bcc51ae1 ggml-backend: Don't recreate the scheduler for each context	2 bulan lalu
Jesse Gross	bd6a7d5e64 ollamarunner: Pass runner performance parameters to backends	2 bulan lalu
Daniel Hiltgen	df2680b4b9 Wire up system info log for new engine (#9123)	2 bulan lalu
Jesse Gross	ed443a0393 Runner for Ollama engine	4 bulan lalu
Jesse Gross	d223f3b697 ggml-backend: Close on nil should be a no-op	2 bulan lalu
Jesse Gross	60830695c2 ggml-backend: Ensure data is available after async computation	2 bulan lalu
Jesse Gross	01d9a46854 ggml-backend: Let GGML allocate context memory	3 bulan lalu
Jesse Gross	d773b7d671 backend: API to support full precision matmul	2 bulan lalu
Jesse Gross	4d4463b2bd backend: Support graph computation that does not return an output	2 bulan lalu
Jesse Gross	0e38297f87 backend: Consistently use int (vs. int64) for tensor shapes	2 bulan lalu
Jesse Gross	7e13f568dc backend: Don't return an error on Close	2 bulan lalu
Michael Yang	58245413f4 next ollama runner (#7913)	2 bulan lalu