ggml : fix Q5_0 quantization
This commit is contained in:
parent
60f62bbc85
commit
8fbf7777ce
1 changed files with 1 additions and 1 deletions
2
ggml.c
2
ggml.c
|
@ -845,7 +845,7 @@ static void quantize_row_q5_0_reference(const float * restrict x, block_q5_0 * r
|
|||
const float d = max / -16;
|
||||
const float id = d ? 1.0f/d : 0.0f;
|
||||
|
||||
y[i].d = d;
|
||||
y[i].d = GGML_FP32_TO_FP16(d);
|
||||
|
||||
uint32_t qh = 0;
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue