CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix loongson compile warnings (#7537)

Browse Source 
* ggml : fix loongson compile warnings

ggml-ci

* Fix loongarch quantize test fail.

Fix unexpected error introduced during rebase code.

* tests : disable json test due to lack of python on the CI node

ggml-ci

---------

Co-authored-by: junchao-loongson <zhaojunchao@loongson.cn>
This commit is contained in:
Georgi Gerganov
2024-05-31 14:17:10 +03:00
committed by GitHub
parent 2e32f874e6
commit 0c27e6f62e
3 changed files with 35 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
ggml.c
View File

@@ -1576,11 +1576,11 @@ do { \
// F16 arithmetic is not supported by AVX, so we use F32 instead
#define GGML_F32Cx8 __m256
#define GGML_F32Cx8 __m256
#define GGML_F32Cx8_ZERO (__m256)__lasx_xvldi(0)
#define GGML_F32Cx8_SET1(x) (__m256)__lasx_xvreplgr2vr_w((x))
static inline __m256 __lasx_f32cx8_load(const ggml_fp16_t *x) {
static inline __m256 __lasx_f32cx8_load(const ggml_fp16_t * x) {
float tmp[8];
for (int i = 0; i < 8; i++) {
@@ -1589,13 +1589,14 @@ static inline __m256 __lasx_f32cx8_load(const ggml_fp16_t *x) {
return (__m256)__lasx_xvld(tmp, 0);
}
static inline void __lasx_f32cx8_store(ggml_fp16_t *x, __m256 y) {
static inline void __lasx_f32cx8_store(ggml_fp16_t * x, __m256 y) {
float arr[8];
__lasx_xvst(y, arr, 0);
for (int i = 0; i < 8; i++)
for (int i = 0; i < 8; i++) {
x[i] = GGML_FP32_TO_FP16(arr[i]);
}
}
#define GGML_F32Cx8_LOAD(x) __lasx_f32cx8_load(x)
#define GGML_F32Cx8_STORE(x, y) __lasx_f32cx8_store(x, y)
@@ -1671,7 +1672,7 @@ static inline void __lasx_f32cx8_store(ggml_fp16_t *x, __m256 y) {
#define GGML_F16_STEP 32
#define GGML_F16_EPR 4
static inline __m128 __lsx_f16x4_load(ggml_fp16_t *x) {
static inline __m128 __lsx_f16x4_load(const ggml_fp16_t * x) {
float tmp[4];
tmp[0] = GGML_FP16_TO_FP32(x[0]);
@@ -1682,7 +1683,7 @@ static inline __m128 __lsx_f16x4_load(ggml_fp16_t *x) {
return __lsx_vld(tmp, 0);
}
static inline void __lsx_f16x4_store(ggml_fp16_t *x, __m128 y) {
static inline void __lsx_f16x4_store(ggml_fp16_t * x, __m128 y) {
float arr[4];
__lsx_vst(y, arr, 0);