OpenSource/ollama

Auteur	SHA1 Message	Date
Patrick Devine	4cc3be3035 Move envconfig and consolidate env vars (#4608)	il y a 11 mois
Jeffrey Morgan	38255d2af1 Use flash attention flag for now (#4580)	il y a 11 mois
Patrick Devine	6845988807 Ollama `ps` command for showing currently loaded models (#4327)	il y a 11 mois
Daniel Hiltgen	0a954e5066 Fix stale test logic	il y a 1 an
Jeffrey Morgan	dfa2f32ca0 unload in critical section (#4187)	il y a 1 an
Daniel Hiltgen	f56aa20014 Centralize server config handling	il y a 1 an
Daniel Hiltgen	9a32c514cb Soften timeouts on sched unit tests	il y a 1 an
Daniel Hiltgen	d6e3b64582 Fix concurrency for CPU mode	il y a 1 an
Jeffrey Morgan	00b0699c75 Reload model if `num_gpu` changes (#3920)	il y a 1 an
Bryce Reitano	36a6daccab Restructure loading conditional chain	il y a 1 an
Bryce Reitano	ceb0e26e5e Provide variable ggml for TestLoad	il y a 1 an
Bryce Reitano	284e02bed0 Move ggml loading to when we attempt fitting	il y a 1 an
Daniel Hiltgen	d8851cb7a0 Harden sched TestLoad	il y a 1 an
Daniel Hiltgen	34b9db5afc Request and model concurrency	il y a 1 an