Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

Fix ARM_NEON

Browse Source
This commit is contained in:
Iwan Kawrakow 2024-03-02 10:12:02 +02:00
parent 93bce3c909
commit d4dfc250cc
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-quants.c
View File

@ -10106,7 +10106,7 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
const uint8x16_t mask2 = vld1q_u8(k_mask2); const uint8x16_t mask2 = vld1q_u8(k_mask2);
const int16x8_t hshift = vld1q_s16(k_shift); const int16x8_t hshift = vld1q_s16(k_shift);
const uint16x8_t m256 = vdupq_n_u16(256); const uint16x8_t m256 = vdupq_n_u16(256);
const uint16x8_t m1 = vdupq_n_u8(1); const uint8x16_t m1 = vdupq_n_u8(1);
uint8x16x2_t vs; uint8x16x2_t vs;
ggml_int8x16x4_t q3s; ggml_int8x16x4_t q3s;