From a867b919ca1e26cc828f98c35b4c6926e8e54762 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Sat, 21 Dec 2024 08:32:39 +0100 Subject: IQ2_XS_R4 (#155) * iq2_xs_r4: Zen4 * iq2_xs_r4: AVX2 * iq2_xs_r4: slightly better matrix x vector on AVX2 * iq2_xs_r4: NEON - not much better than iq2_xs * iq2_xs_r4: slightly better NEON --------- Co-authored-by: Iwan Kawrakow --- ggml/include/ggml.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'ggml/include') diff --git a/ggml/include/ggml.h b/ggml/include/ggml.h index 42fbcea2..60f787ad 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -419,6 +419,7 @@ extern "C" { GGML_TYPE_Q5_K_R4 = 213, GGML_TYPE_Q6_K_R4 = 214, GGML_TYPE_IQ2_XXS_R4= 216, + GGML_TYPE_IQ2_XS_R4 = 217, GGML_TYPE_IQ3_XXS_R4= 218, GGML_TYPE_IQ4_NL_R4 = 220, GGML_TYPE_IQ4_XS_R4 = 223, @@ -499,6 +500,7 @@ extern "C" { GGML_FTYPE_MOSTLY_Q5_K_R4 = 213, // except 1d tensors GGML_FTYPE_MOSTLY_Q6_K_R4 = 214, // except 1d tensors GGML_FTYPE_MOSTLY_IQ2_XXS_R4= 215, // except 1d tensors + GGML_FTYPE_MOSTLY_IQ2_XS_R4 = 216, // except 1d tensors GGML_FTYPE_MOSTLY_IQ3_XXS_R4= 217, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_NL_R4 = 219, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_XS_R4 = 222, // except 1d tensors -- cgit v1.2.3