From 415a7cf6c30ab0534de29a53a2b34462875c91f4 Mon Sep 17 00:00:00 2001 From: Iwan Kawrakow Date: Wed, 11 Jun 2025 10:55:42 +0300 Subject: [PATCH] NEON is not working yet, so still use Q8_K GEMM --- ggml/src/ggml.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/ggml/src/ggml.c b/ggml/src/ggml.c index ba4ae8a7..9e3c4b90 100644 --- a/ggml/src/ggml.c +++ b/ggml/src/ggml.c @@ -1067,7 +1067,11 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = { .from_float = quantize_row_iq2_xxs, .from_float_ref = (ggml_from_float_t)quantize_row_iq2_xxs_ref, .vec_dot = ggml_vec_dot_iq2_xxs_q8_K, - .vec_dot_type = GGML_TYPE_Q8_2_X4, //GGML_TYPE_Q8_K, +#ifdef __AVX2__ + .vec_dot_type = GGML_TYPE_Q8_2_X4, +#else + .vec_dot_type = GGML_TYPE_Q8_K, +#endif .nrows = 1, .row_meta_size = 0, },