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 --- 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 67f54da7..f4f375c9 100644 --- a/ggml/src/ggml-quants.c +++ b/ggml/src/ggml-quants.c @@ -15203,6 +15203,7 @@ bool ggml_validate_row_data(enum ggml_type type, const void * data, size_t nbyte case GGML_TYPE_Q6_0_R4: break; case GGML_TYPE_Q8_0_R4: break; case GGML_TYPE_Q4_K_R4: break; + case GGML_TYPE_Q5_K_R4: break; case GGML_TYPE_Q6_K_R4: break; case GGML_TYPE_Q4_0_4_4: case GGML_TYPE_Q4_0_4_8: -- cgit v1.2.3