From 16a020ce1e2cb1cd58268397dbd9e6eeb6ee0699 Mon Sep 17 00:00:00 2001 From: xrip Date: Sun, 6 Sep 2026 16:24:17 +0000 Subject: [PATCH] ggml-cpu: add AVX1 Q4_K and IQ4_XS paths Add AVX1 CPU kernels for the Q4_K and IQ4_XS quantized matrix paths. The Q4_K changes add panel repacking and prefill support. The IQ4_XS changes decode eight-row panels with AVX1 intrinsics and select the path only when AVX is available. Existing fallback paths remain in place for CPUs without AVX and for other quant types. --- ggml/src/ggml-cpu/arch-fallback.h | 1 - 1 file changed, 1 deletion(-) diff --git a/ggml/src/ggml-cpu/arch-fallback.h b/ggml/src/ggml-cpu/arch-fallback.h index 91dcc0149..c14456f9c 100644 --- a/ggml/src/ggml-cpu/arch-fallback.h +++ b/ggml/src/ggml-cpu/arch-fallback.h @@ -90,7 +90,6 @@ #define ggml_vec_dot_q2_0_q8_0_generic ggml_vec_dot_q2_0_q8_0 // repack.cpp #define ggml_quantize_mat_q8_0_4x4_generic ggml_quantize_mat_q8_0_4x4 -#define ggml_quantize_mat_q8_K_4x4_generic ggml_quantize_mat_q8_K_4x4 #define ggml_gemv_q1_0_4x4_q8_0_generic ggml_gemv_q1_0_4x4_q8_0 #define ggml_gemv_q1_0_4x8_q8_0_generic ggml_gemv_q1_0_4x8_q8_0 #define ggml_gemv_q4_0_4x4_q8_0_generic ggml_gemv_q4_0_4x4_q8_0