From e0adb8b1227dd4622a91a5b3680b4af2e36d32f4 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Wed, 11 Dec 2024 11:19:00 +0100 Subject: Q3_K_R4 (#134) * q3_k_r4: Zen4 works, but not as good as it should be 238 t/s, so sloghtly slower than q6_k_r4. * q3_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 106.9 t/s. This is 1.93X faster than q3_K_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 7290f18f..f87d13ff 100644 --- a/include/llama.h +++ b/include/llama.h @@ -183,6 +183,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors + LLAMA_FTYPE_MOSTLY_Q3_K_R4 = 211, // 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 -- cgit v1.2.3