root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-29 04:44:34 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

ggml : minor formatting

Browse Source
This commit is contained in:
Georgi Gerganov 2023-05-07 20:00:01 +03:00
parent 7cdc08a5d1
commit 60f62bbc85
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 14 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
ggml.c
View File

@ -1283,7 +1283,7 @@ static void dequantize_row_q4_0(const block_q4_0 * restrict x, float * restrict
const float d = x[i].d; const float d = x[i].d;
for (int j = 0; j < qk/2; ++j) { for (int j = 0; j < qk/2; ++j) {
const int x0 = (x[i].qs[j] & 0xf) - 8; const int x0 = (x[i].qs[j] & 0x0F) - 8;
const int x1 = (x[i].qs[j] >> 4) - 8; const int x1 = (x[i].qs[j] >> 4) - 8;
y[i*qk + j + 0 ] = x0*d; y[i*qk + j + 0 ] = x0*d;
@ -1304,7 +1304,7 @@ static void dequantize_row_q4_1(const block_q4_1 * restrict x, float * restrict
const float m = x[i].m; const float m = x[i].m;
for (int j = 0; j < qk/2; ++j) { for (int j = 0; j < qk/2; ++j) {
const int x0 = (x[i].qs[j] & 0xf); const int x0 = (x[i].qs[j] & 0x0F);
const int x1 = (x[i].qs[j] >> 4); const int x1 = (x[i].qs[j] >> 4);
y[i*qk + j + 0 ] = x0*d + m; y[i*qk + j + 0 ] = x0*d + m;
@ -1330,7 +1330,7 @@ static void dequantize_row_q5_0(const block_q5_0 * restrict x, float * restrict
const uint8_t xh_0 = ((qh & (1u << (j + 0 ))) >> (j + 0 )) << 4; const uint8_t xh_0 = ((qh & (1u << (j + 0 ))) >> (j + 0 )) << 4;
const uint8_t xh_1 = ((qh & (1u << (j + 16))) >> (j + 12)); const uint8_t xh_1 = ((qh & (1u << (j + 16))) >> (j + 12));
const int32_t x0 = ((x[i].qs[j] & 0xf) | xh_0) - 16; const int32_t x0 = ((x[i].qs[j] & 0x0F) | xh_0) - 16;
const int32_t x1 = ((x[i].qs[j] >> 4) | xh_1) - 16; const int32_t x1 = ((x[i].qs[j] >> 4) | xh_1) - 16;
y[i*qk + j + 0 ] = x0*d; y[i*qk + j + 0 ] = x0*d;
@ -1357,7 +1357,7 @@ static void dequantize_row_q5_1(const block_q5_1 * restrict x, float * restrict
const uint8_t xh_0 = ((qh & (1u << (j + 0 ))) >> (j + 0 )) << 4; const uint8_t xh_0 = ((qh & (1u << (j + 0 ))) >> (j + 0 )) << 4;
const uint8_t xh_1 = ((qh & (1u << (j + 16))) >> (j + 12)); const uint8_t xh_1 = ((qh & (1u << (j + 16))) >> (j + 12));
const int x0 = (x[i].qs[j] & 0xf) | xh_0; const int x0 = (x[i].qs[j] & 0x0F) | xh_0;
const int x1 = (x[i].qs[j] >> 4) | xh_1; const int x1 = (x[i].qs[j] >> 4) | xh_1;
y[i*qk + j + 0 ] = x0*d + m; y[i*qk + j + 0 ] = x0*d + m;
@ -2184,7 +2184,7 @@ static void ggml_vec_dot_q4_0_q8_0(const int n, float * restrict s, const void *
int sumi = 0; int sumi = 0;
for (int j = 0; j < qk/2; ++j) { for (int j = 0; j < qk/2; ++j) {
const int v0 = (x[i].qs[j] & 0xf) - 8; const int v0 = (x[i].qs[j] & 0x0F) - 8;
const int v1 = (x[i].qs[j] >> 4) - 8; const int v1 = (x[i].qs[j] >> 4) - 8;
sumi += (v0 * y[i].qs[j]) + (v1 * y[i].qs[j + qk/2]); sumi += (v0 * y[i].qs[j]) + (v1 * y[i].qs[j + qk/2]);
@ -2306,7 +2306,7 @@ static void ggml_vec_dot_q4_1_q8_1(const int n, float * restrict s, const void *
int sumi = 0; int sumi = 0;
for (int j = 0; j < qk/2; ++j) { for (int j = 0; j < qk/2; ++j) {
const int v0 = (x[i].qs[j] & 0xf); const int v0 = (x[i].qs[j] & 0x0F);
const int v1 = (x[i].qs[j] >> 4); const int v1 = (x[i].qs[j] >> 4);
sumi += (v0 * y[i].qs[j]) + (v1 * y[i].qs[j + qk/2]); sumi += (v0 * y[i].qs[j]) + (v1 * y[i].qs[j + qk/2]);
@ -2487,7 +2487,7 @@ static void ggml_vec_dot_q5_0_q8_0(const int n, float * restrict s, const void *
const uint8_t xh_0 = ((qh & (1u << (j + 0 ))) >> (j + 0 )) << 4; const uint8_t xh_0 = ((qh & (1u << (j + 0 ))) >> (j + 0 )) << 4;
const uint8_t xh_1 = ((qh & (1u << (j + 16))) >> (j + 12)); const uint8_t xh_1 = ((qh & (1u << (j + 16))) >> (j + 12));
const int32_t x0 = ((x[i].qs[j] & 0xf) | xh_0) - 16; const int32_t x0 = ((x[i].qs[j] & 0x0F) | xh_0) - 16;
const int32_t x1 = ((x[i].qs[j] >> 4) | xh_1) - 16; const int32_t x1 = ((x[i].qs[j] >> 4) | xh_1) - 16;
sumi += (x0 * y[i].qs[j]) + (x1 * y[i].qs[j + qk/2]); sumi += (x0 * y[i].qs[j]) + (x1 * y[i].qs[j + qk/2]);