cturan/llama.cpp

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

作者	SHA1 備註	提交日期
Georgi Gerganov	745f11fed0 memory : correctly handle failure in apply() (#14438)	6 月之前
Georgi Gerganov	3e63a58ef7 kv-cache : refactor the update/defrag mechanism (#13988)	7 月之前
Georgi Gerganov	e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)	10 月之前