From 167479e0272dcb5f9babc7668664fa2a75c4f2dd Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Mon, 23 Dec 2024 14:34:23 +0100 Subject: IQ3_S_R4 (#162) * iq3_s_r4: WIP * iq3_s_r4: Zen4 * iq3_s_r4: slightly better Zen4 * iq3_s_r4: AVX2 * iq3_s_r4: NEON * iq3_s_r4: rearrange quants * iq3_s_r4: rearranged quants - AVX2 * iq3_s_r4: rearranged quants - 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 002388cb..5fd8324d 100644 --- a/ggml/include/ggml.h +++ b/ggml/include/ggml.h @@ -422,6 +422,7 @@ extern "C" { GGML_TYPE_IQ2_XS_R4 = 217, GGML_TYPE_IQ3_XXS_R4= 218, GGML_TYPE_IQ4_NL_R4 = 220, + GGML_TYPE_IQ3_S_R4 = 221, GGML_TYPE_IQ2_S_R4 = 222, GGML_TYPE_IQ4_XS_R4 = 223, GGML_TYPE_BF16_R16 = 230, @@ -504,6 +505,7 @@ extern "C" { 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_IQ3_S_R4 = 220, // except 1d tensors GGML_FTYPE_MOSTLY_IQ2_S_R4 = 221, // except 1d tensors GGML_FTYPE_MOSTLY_IQ4_XS_R4 = 222, // except 1d tensors GGML_FTYPE_MOSTLY_BF16_R16 = 224, // except 1d tensors -- cgit v1.2.3