From d69344f8ea72c6fe6ec16300b939586fa9633e2e Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Tue, 17 Dec 2024 07:51:11 +0100 Subject: IQ3_K_R4 (#145) * iq3_k_r4 WIP * iq3_k_r4: Zen4 * iq3_k_r4: AVX2 * iq3_k_r4: NEON * iq3_k_r4: faster matrix x vector multiplication on NEON --------- Co-authored-by: Iwan Kawrakow --- include/llama.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/llama.h') diff --git a/include/llama.h b/include/llama.h index 988ffec7..026cf08e 100644 --- a/include/llama.h +++ b/include/llama.h @@ -193,6 +193,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q6_0_R4 = 335, // except 1d tensors LLAMA_FTYPE_MOSTLY_BF16_R16 = 232, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ2_BN_R4 = 337, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ3_K_R4 = 339, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_K_R4 = 340, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q8_K_R8 = 399, // except 1d tensors -- cgit v1.2.3