root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-12 19:50:17 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Minor, plus rebase on master

Browse Source
This commit is contained in:
Iwan Kawrakow 2023-04-21 18:09:43 +02:00 committed by Georgi Gerganov
parent e435bfd93c
commit a0242a833c
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

@ -2012,7 +2012,7 @@ static const quantize_fns_t quantize_fns[GGML_TYPE_COUNT] = {
[GGML_TYPE_Q4_3] = {
.dequantize_row_q = dequantize_row_q4_3,
.quantize_row_q = quantize_row_q4_3,
.quantize_row_q_reference = (quantize_row_q_t) quantize_row_q4_3_reference, // TODO: RMSE optimization
.quantize_row_q_reference = (quantize_row_q_t) quantize_row_q4_3_reference,
.quantize_row_q_dot = quantize_row_q8_0,
.vec_dot_q = ggml_vec_dot_q4_3_q8_0,
},