From a63a96b5aea031f9dabf1e7c8d5ee28af170e9e7 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Tue, 10 Dec 2024 18:13:47 +0100 Subject: Q5_K_R4 (#132) * q5_k_r4: WIP * q5_k_r4: Zen4 and AVX2 We get PP-512(LLaMA-3.1-8B) = 248.3 t/s on Zen4. Q5_K_S has PP-512 = 190 t/s. * q5_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 96.1 t/s. --------- 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 92234d6c..7290f18f 100644 --- a/include/llama.h +++ b/include/llama.h @@ -184,6 +184,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors 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_IQ4_NL_R4 = 225, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors -- cgit v1.2.3