Skip to content

Commit 93e6718

Browse files
xctanggerganov
andcommitted
fix a typo in arm version of ggml_vec_dot_q4_K_q8_K
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 parent 2573662 commit 93e6718

File tree

1 file changed

+4
-0
lines changed

1 file changed

+4
-0
lines changed

ggml/src/ggml-cpu/arch/arm/quants.c

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2124,7 +2124,11 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi
21242124

21252125
void ggml_vec_dot_q4_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) {
21262126
assert(n % QK_K == 0);
2127+
#ifdef __ARM_FEATURE_MATMUL_INT8
2128+
assert((nrc == 2) || (nrc == 1));
2129+
#else
21272130
assert(nrc == 1);
2131+
#endif
21282132
UNUSED(nrc);
21292133
UNUSED(bx);
21302134
UNUSED(by);

0 commit comments

Comments
 (0)