cturan/llama.cpp

kopia lustrzana https://github.com/cturan/llama.cpp

Autor	SHA1 Wiadomość	Data
Qingyou Meng	1d656d6360 ggml : change ggml_graph_compute() API to not require context (#1999)	2 lat temu
Georgi Gerganov	1b6efeab82 tests : fix test-grad0	2 lat temu
Georgi Gerganov	65bdd52a86 tests : sync test-grad0 from ggml	2 lat temu
xaedes	e32089b2c2 train : improved training-from-scratch example (#1652)	2 lat temu
xaedes	f954edda93 ggml : implement backward pass for llama + small training-llama-from-scratch example (#1360)	2 lat temu