From 8c6b84220d78d1742cbe55e21746ad68c8df267a Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Wed, 11 Dec 2024 18:16:49 +0100 Subject: Q2_K_R4 (#136) * q2_k_r4: Zen4 PP-512(LLaMA-3.1-8B) = 256 t/s * q3_k_r4: AVX2 * q2_k_r4: AVX2 We get PP-512(LLaMA-3.1-8B) = 287 t/s. Also cherry-picked the q3_k_r4 AVX2 adaptation that I somehow forgot to push upstream. * q2_k_r4: NEON We get PP-512(LLaMA-3.1-8B) = 106.2 t/s. TG-128 is 36.02 t/s, which is ~10% higher than q2_K_S. * Make sure rows per thread are a multiple of 4 --------- 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 c2fdf6fa..ff857087 100644 --- a/ggml/src/ggml-quants.c +++ b/ggml/src/ggml-quants.c @@ -15202,6 +15202,7 @@ bool ggml_validate_row_data(enum ggml_type type, const void * data, size_t nbyte case GGML_TYPE_Q5_0_R4: break; case GGML_TYPE_Q6_0_R4: break; case GGML_TYPE_Q8_0_R4: break; + case GGML_TYPE_Q2_K_R4: break; case GGML_TYPE_Q3_K_R4: break; case GGML_TYPE_Q4_K_R4: break; case GGML_TYPE_Q5_K_R4: break; -- cgit v1.2.3