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

oops

Browse source 
oops
This commit is contained in:
netrunnereve 2024-04-29 22:45:59 -04:00
parent 8916954a82
commit ae0b5ea7ae
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
sgemm.cpp
View file

@ -725,7 +725,7 @@ class tinyBLAS_Q0_AVX {
__m256 Cv[RN][RM] = {}; __m256 Cv[RN][RM] = {};
for (int64_t l = 0; l < k; ++l) for (int64_t l = 0; l < k; ++l)
for (int64_t j = 0; j < RN; ++j) for (int64_t j = 0; j < RN; ++j)
for (int64_t i = 0; i < RM; ++i) for (int64_t i = 0; i < RM; ++i) {
#if defined(__AVX2__) #if defined(__AVX2__)
__m256 udTmp = updot(_mm256_sign_epi8(load(A + lda * (ii + i) + l), __m256 udTmp = updot(_mm256_sign_epi8(load(A + lda * (ii + i) + l),
load(A + lda * (ii + i) + l)), load(A + lda * (ii + i) + l)),