mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-04 10:47:38 +02:00
Alberto Cabrera PérezandGeorgi Gerganov
cd8370b408
* Enabled q4_K_4x8 path * Fixed generic Q4_K 8x4 implementation * wip: dotprod gemm * Working arm q4_K dotprod gemm Signed-off-by: Alberto Cabrera <[email protected]> * Undo acc rename Signed-off-by: Alberto Cabrera <[email protected]> * Q4_K arm dotprod gemm Signed-off-by: Alberto Cabrera <[email protected]> * Fix: q4_qs reinterpret from uint to int Signed-off-by: Alberto Cabrera <[email protected]> * Removed comments * Fixed macro guards * Fixed unused vars in generic implementation * Fixed unused vars in 8x4 repack * Fixed unused vars in generic implementation, unneeded comment * Missing arch fallback for x86 * minor : style --------- Signed-off-by: Alberto Cabrera <[email protected]> Co-authored-by: Georgi Gerganov <[email protected]>