aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-11-09 23:29:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

ggml : fix NEON signs (close #620, #622)

Browse source
This commit is contained in:
Georgi Gerganov 2023-03-30 20:27:32 +03:00
parent ed3c680bcd
commit 77efdf5a50
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
ggml.c
View file

@ -1038,8 +1038,8 @@ static void dequantize_row_q4_1(const void * restrict vx, float * restrict y, in
const uint8x16_t vq = vcombine_u8(vx_0, vx_1); const uint8x16_t vq = vcombine_u8(vx_0, vx_1);
// convert to 2x uint16x8_t // convert to 2x uint16x8_t
const uint16x8_t vi_0 = vmovl_s8(vget_low_u8 (vq)); const uint16x8_t vi_0 = vmovl_u8(vget_low_u8 (vq));
const uint16x8_t vi_1 = vmovl_s8(vget_high_u8(vq)); const uint16x8_t vi_1 = vmovl_u8(vget_high_u8(vq));
// convert to 4x float32x4_t // convert to 4x float32x4_t
const float32x4_t vf_0 = vcvtq_f32_u32(vmovl_u16(vget_low_u16 (vi_0))); const float32x4_t vf_0 = vcvtq_f32_u32(vmovl_u16(vget_low_u16 (vi_0)));