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

Update ggml/src/ggml-cpu/ggml-cpu-quants.c

Browse source 
change to use K_SCALE_SIZE

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
fj-y-saito 2025-01-15 12:13:17 +09:00 • committed by GitHub
parent 5f98b7c31b
commit 964f81173d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-cpu/ggml-cpu-quants.c
View file

@ -5582,7 +5582,7 @@ void ggml_vec_dot_q4_K_q8_K(int n, float * restrict s, size_t bs, const void * r
const int16x8_t q8sums = vpaddq_s16(vld1q_s16(y[i].bsums), vld1q_s16(y[i].bsums + 8));
memcpy(utmp, x[i].scales, 12);
memcpy(utmp, x[i].scales, K_SCALE_SIZE);
uint32x2_t mins8 = { 0 };
mins8 = vset_lane_u32(utmp[1] & kmask1, mins8, 0);