From f64de08203aaee95ca755336de3e1db85d990198 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Wed, 4 Dec 2024 15:20:07 +0100 Subject: IQ4_XS_R4 (#123) * Adding iq4_xs_r4 This is a 1st working version on Zen4. We get PP-512(LLaMA-3.1-8B) = 226 t/s, so 16% slower than iq4_nl_x4. * iq4_xs_r4: WIP * iq4_xs_r4: Use AVX2 version for matrix x vector on Zen4 * iq4_xs_r4: NEON We get PP-512(LLaMA-3.1-8B) = 115.6 t/s on M2-Max, up from 68.2 t/s for iq4_xs! * DRY --------- 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 bf843ad2..77c988a5 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_IQ4_NL_X4 = 225, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q6_0_R4 = 235, // except 1d tensors LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file -- cgit v1.2.3