Concedo 33809c9e82 doing what i must because i can, after the mess that is https://github.com/ggml-org/llama.cpp/pull/13892 ... there is so much duplicate code in each cpu arch, i expect upstream will prune it eventually arch detection has no fallback if all the arches are not found, by right we should set GGML_CPU_GENERIC i should be relaxing its the weekend		2025-06-14 01:41:16 +08:00
..
include	Merge branch 'upstream' into concedo_experimental	2025-06-02 23:26:43 +08:00
src	doing what i must because i can, after the mess that is https://github.com/ggml-org/llama.cpp/pull/13892	2025-06-14 01:41:16 +08:00