mirror of
https://github.com/ggml-org/whisper.cpp.git
synced 2026-10-13 01:35:40 +02:00
* ggml-cpu: vectorize BF16 K tails in tinyBLAS * tests: Skip tinyBLAS when use_ref is enabled so CPU tests compare against the vec_dot path. * ggml-cpu: vectorize tinyBLAS F16/F32 tails