root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

ggml : fix scalar implementation of Q4_1 dot

Browse Source
This commit is contained in:
Georgi Gerganov 2023-05-20 10:13:19 +03:00
parent 2d5db48371
commit 4fd3e29297
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

@ -2481,7 +2481,7 @@ static void ggml_vec_dot_q4_1_q8_1(const int n, float * restrict s, const void *
sumi += (v0 * y[i].qs[j]) + (v1 * y[i].qs[j + qk/2]);
}
sumf += (GGML_FP16_TO_FP32(x[i]).d*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s;
sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s;
}
*s = sumf;