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

ggml: fix IQ3_S AVX implementation

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-03-02 19:32:19 +02:00
parent 4d4d2366fc
commit 55ac610c7f
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-quants.c
View file

@ -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]],