From 42f70cb2f6a8089e0a0560a459e4ba317bac4d49 Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Mon, 24 Jul 2023 12:55:02 +0300 Subject: [PATCH] Fix scalar version of Q5_K when QK_K = 64 (#2362) Co-authored-by: Iwan Kawrakow --- k_quants.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/k_quants.c b/k_quants.c index c576fd7a7..e790abf88 100644 --- a/k_quants.c +++ b/k_quants.c @@ -3297,8 +3297,7 @@ void ggml_vec_dot_q5_K_q8_K(const int n, float * restrict s, const void * restri #else - - uint8_t aux8[QK_K]; + int8_t aux8[QK_K]; int16_t aux16[16]; float sums [8]; memset(sums, 0, 8*sizeof(float)); @@ -3308,7 +3307,7 @@ void ggml_vec_dot_q5_K_q8_K(const int n, float * restrict s, const void * restri const uint8_t * restrict q4 = x[i].qs; const uint8_t * restrict hm = x[i].qh; const int8_t * restrict q8 = y[i].qs; - uint8_t * restrict a = aux8; + int8_t * restrict a = aux8; for (int l = 0; l < 32; ++l) { a[l+ 0] = q4[l] & 0xF; a[l+32] = q4[l] >> 4;