cturan/llama.cpp

огледало от https://github.com/cturan/llama.cpp

Автор	SHA1 Съобщение	Дата
Georgi Gerganov	cd5e3b5754 server : support unified cache across slots (#16736)	преди 2 месеца
Acly	d8eaa26e4d tests : fix test-thread-safety when compiling with multiple backends (#16699)	преди 2 месеца
Georgi Gerganov	00131d6eaf tests : update for LLAMA_SET_ROWS=1 (#14961)	преди 5 месеца
Diego Devesa	6adc3c3ebc llama : add thread safety test (#14035)	преди 7 месеца