From 239a344f9935cb614c6208000edb0815214286a1 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Mon, 2 Dec 2024 17:01:48 +0100 Subject: Q4_0_R4 (#119) * Adding iq4_0_r4 - q4_0 repacked We get PP-512(LLaMA-3.1-8B) = 278 t/s on a Ryzen-7950X CPU, so ~5-6% faster than iq4_nl_x4. * q4_0_r4: NEON Here we get 115.8 t/s, so also ~5% better than iq4_nl_x4. --------- Co-authored-by: Iwan Kawrakow --- ggml/src/ggml-quants.c | 1 + 1 file changed, 1 insertion(+) (limited to 'ggml/src/ggml-quants.c') diff --git a/ggml/src/ggml-quants.c b/ggml/src/ggml-quants.c index 376c97f8..dd43e1c1 100644 --- a/ggml/src/ggml-quants.c +++ b/ggml/src/ggml-quants.c @@ -15197,6 +15197,7 @@ bool ggml_validate_row_data(enum ggml_type type, const void * data, size_t nbyte case GGML_TYPE_IQ4_KS: break; case GGML_TYPE_IQ4_KSS: break; case GGML_TYPE_IQ4_NL_X4: break; + case GGML_TYPE_Q4_0_R4: break; case GGML_TYPE_Q4_0_4_4: case GGML_TYPE_Q4_0_4_8: { -- cgit v1.2.3