cturan/llama.cpp

镜像来自 https://github.com/cturan/llama.cpp

作者	SHA1 備註	提交日期
Georgi Gerganov	cd5e3b5754 server : support unified cache across slots (#16736)	2 月之前
Acly	d8eaa26e4d tests : fix test-thread-safety when compiling with multiple backends (#16699)	2 月之前
Georgi Gerganov	00131d6eaf tests : update for LLAMA_SET_ROWS=1 (#14961)	5 月之前
Diego Devesa	6adc3c3ebc llama : add thread safety test (#14035)	7 月之前