diff --git a/ggml-quants.c b/ggml-quants.c index d07327b42..0126c5d96 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -7537,6 +7537,9 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * restrict s, size_t bs, const void * r int bit = 0; int is = 0; + const uint8_t * restrict q3 = x[i].qs; + const int8_t * restrict q8 = y[i].qs; + for (int j = 0; j < QK_K/128; ++j) { // load low 2 bits const __m256i q3bits = __lasx_xvld((const __m256i*)q3, 0); q3 += 32;