From 4b53bc876eda6d89890711998b3ab5bf033b2199 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Fri, 20 Dec 2024 12:02:42 +0100 Subject: IQ2_XXS_R4 (#154) * iq2_xxs_r4: Zen4 Disapointing gain: 134.7 t/s -> 151.1 t/s for PP-512 TG-128 is better: 3.45 -> 4.61 t/s @ 1 thread * Minor * iq2_xxs_r4: NEON --------- Co-authored-by: Iwan Kawrakow --- include/llama.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/llama.h b/include/llama.h index e009ed4e..27d10c14 100644 --- a/include/llama.h +++ b/include/llama.h @@ -188,6 +188,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q4_K_R4 = 214, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q5_K_R4 = 216, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q6_K_R4 = 218, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ2_XXS_R4 = 219, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ3_XXS_R4 = 223, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_NL_R4 = 225, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors -- cgit v1.2.3