vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : fix q6_K FP16 -> FP32 conversion

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-02-22 19:59:05 +02:00
parent 80196bd76c
commit dd04b7c480
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-quants.c
View file

@ -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;