mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-03 03:58:54 +00:00
Fix typos so to call correct vnni functions under vnni condition (#21625)
### Description Fix 2 typos in mlas avx 4bit gemm implementation to call correct vnni functions under vnni condition ### Motivation and Context needed for 1.19.0 release Signed-off-by: liqunfu <liqun.fu@microsoft.com>
This commit is contained in:
parent
1f907a23f0
commit
f6f9657fb6
2 changed files with 3 additions and 3 deletions
|
|
@ -679,9 +679,9 @@ Q4Int8GemmR1xC1BlkLen16Avx512(
|
|||
const __m512i av_01_epi8 = _mm512_loadu_si512((const __m512i*)(QuantAPtr + 64));
|
||||
|
||||
if constexpr (vnni) {
|
||||
accumulate_blklen16_r1c1blk8_avx512(av_00_epi8, av_01_epi8, QuantBDataPtr, QuantAScalePtr, QuantBScalePtr, acc0);
|
||||
} else {
|
||||
accumulate_blklen16_r1c1blk8_avx512vnni(av_00_epi8, av_01_epi8, QuantBDataPtr, QuantAScalePtr, QuantBScalePtr, acc0);
|
||||
} else {
|
||||
accumulate_blklen16_r1c1blk8_avx512(av_00_epi8, av_01_epi8, QuantBDataPtr, QuantAScalePtr, QuantBScalePtr, acc0);
|
||||
}
|
||||
|
||||
QuantAPtr += BlkLen16 * PerAccuBlk8;
|
||||
|
|
|
|||
|
|
@ -721,7 +721,7 @@ Q4Int8GemmR1xC1BlkLen32Avx512(
|
|||
accumulate_blklen32_r1c1blk4_avx512vnni(av_00_epi8, av_01_epi8, QuantBDataPtr, QuantAScalePtr, QuantBScalePtr, acc0);
|
||||
}
|
||||
else {
|
||||
accumulate_blklen32_r1c1blk4_avx512vnni(av_00_epi8, av_01_epi8, QuantBDataPtr, QuantAScalePtr, QuantBScalePtr, acc0);
|
||||
accumulate_blklen32_r1c1blk4_avx512(av_00_epi8, av_01_epi8, QuantBDataPtr, QuantAScalePtr, QuantBScalePtr, acc0);
|
||||
}
|
||||
|
||||
QuantAPtr += BlkLen32 * PerAccuBlk4;
|
||||
|
|
|
|||
Loading…
Reference in a new issue