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

iq1_m: fix Windows ARM

Browse source
This commit is contained in:
Iwan Kawrakow 2024-03-26 05:54:03 +02:00
parent 22fa121344
commit b68f32b391
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

@ -9818,7 +9818,7 @@ void ggml_vec_dot_iq1_m_q8_K (int n, float * restrict s, size_t bs, const void
const int32x4_t p4 = vpaddq_s32(ggml_vdotq_s32(mzero, deltas.val[aux8[2]], q8b.val[2]), ggml_vdotq_s32(mzero, deltas.val[aux8[3]], q8b.val[3])); const int32x4_t p4 = vpaddq_s32(ggml_vdotq_s32(mzero, deltas.val[aux8[2]], q8b.val[2]), ggml_vdotq_s32(mzero, deltas.val[aux8[3]], q8b.val[3]));
const int32x4_t p34 = vpaddq_s32(p3, p4); const int32x4_t p34 = vpaddq_s32(p3, p4);
int32x4_t scales_4 = {sc[ib/2] >> 0, sc[ib/2] >> 3, sc[ib/2] >> 6, sc[ib/2] >> 9}; int32x4_t scales_4 = ggml_vld1q_u32(sc[ib/2] >> 0, sc[ib/2] >> 3, sc[ib/2] >> 6, sc[ib/2] >> 9);
scales_4 = vaddq_s32(vshlq_n_s32(vandq_s32(scales_4, mask), 1), mone); scales_4 = vaddq_s32(vshlq_n_s32(vandq_s32(scales_4, mask), 1), mone);
sumi1 = vmlaq_s32(sumi1, scales_4, p12); sumi1 = vmlaq_s32(sumi1, scales_4, p12);