root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-13 04:00:16 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Remove double lines

Browse Source
This commit is contained in:
Aidan 2024-06-17 10:16:10 +01:00
parent ff076b8873
commit 4a481556e6
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
ggml-sycl.cpp
View File

@ -4297,7 +4297,8 @@ static void dequantize_block_q3_K(const void * __restrict__ vx, dst_t * __restri
static inline void get_scale_min_k4(int j, const uint8_t * q, uint8_t & d, uint8_t & m) {
if (j < 4) {
d = q[j] & 63; m = q[j + 4] & 63;
d = q[j] & 63;
m = q[j + 4] & 63;
} else {
d = (q[j+4] & 0xF) | ((q[j-4] >> 6) << 4);
m = (q[j+4] >> 4) | ((q[j-0] >> 6) << 4);
@ -4327,9 +4328,11 @@ static void dequantize_block_q4_K(const void * __restrict__ vx, dst_t * __restri
uint8_t sc, m;
get_scale_min_k4(is + 0, x[i].scales, sc, m);
const float d1 = dall * sc; const float m1 = dmin * m;
const float d1 = dall * sc;
const float m1 = dmin * m;
get_scale_min_k4(is + 1, x[i].scales, sc, m);
const float d2 = dall * sc; const float m2 = dmin * m;
const float d2 = dall * sc;
const float m2 = dmin * m;
for (int l = 0; l < n; ++l) {
y[l + 0] = d1 * (q[l] & 0xF) - m1;
y[l +32] = d2 * (q[l] >> 4) - m2;