From dd04b7c480252f6f63cd922929ed1b7f600b6043 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Thu, 22 Feb 2024 19:59:05 +0200 Subject: [PATCH] ggml : fix q6_K FP16 -> FP32 conversion ggml-ci --- ggml-quants.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ggml-quants.c b/ggml-quants.c index e62ef70e9..272b0272a 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -8508,7 +8508,7 @@ void ggml_vec_dot_q6_K_q8_K(int n, float * restrict s, size_t bs, const void * r for (int i = 0; i < nb; ++i) { - const float d_all = (float)x[i].d; + const float d_all = GGML_FP16_TO_FP32(x[i].d); const uint8_t * restrict q6 = x[i].ql; const uint8_t * restrict qh = x[i].qh;