Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-11 21:10:24 +01:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix Q5_0 quantization

Browse Source
This commit is contained in:
Georgi Gerganov 2023-05-07 20:26:02 +03:00
parent 60f62bbc85
commit 8fbf7777ce
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml.c
View File

@ -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 d = max / -16;
const float id = d ? 1.0f/d : 0.0f; 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; uint32_t qh = 0;