diff options
author | Georgi Gerganov <ggerganov@gmail.com> | 2024-03-02 20:00:49 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-03-02 20:00:49 +0200 |
commit | 494c87032613e31c0be99b2735e732871f2c4e4d (patch) | |
tree | 6a8e38e52fa48ad174ee3061c97ae896c2aac8c8 | |
parent | 4d4d2366fc9c54d4a275065cfe9299c6cf7c5b78 (diff) |
ggml : fix IQ3_S AVX implementation (#5834)
ggml-ci
-rw-r--r-- | ggml-quants.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/ggml-quants.c b/ggml-quants.c index 492a1b9a..2a8881d7 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -10231,7 +10231,7 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v //const __m256i q2_2 = _mm256_i32gather_epi32((const int *)iq3s_grid, idx.vec[1], 4); const __m256i q2_1 = _mm256_set_epi32( iq3s_grid[idx.index[7]], iq3s_grid[idx.index[6]], iq3s_grid[idx.index[5]], iq3s_grid[idx.index[4]], - iq3s_grid[idx.index[3]], iq3s_grid[idx.index[1]], iq3s_grid[idx.index[1]], iq3s_grid[idx.index[0]] + iq3s_grid[idx.index[3]], iq3s_grid[idx.index[2]], iq3s_grid[idx.index[1]], iq3s_grid[idx.index[0]] ); const __m256i q2_2 = _mm256_set_epi32( iq3s_grid[idx.index[15]], iq3s_grid[idx.index[14]], iq3s_grid[idx.index[13]], iq3s_grid[idx.index[12]], |