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

Merge branch 'master' into compilade/refactor-kv-cache

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-04-09 20:22:19 -04:00
commit d66849f628
82 changed files with 6417 additions and 3307 deletions
Download patch file Download diff file Expand all files Collapse all files

16
ggml.c
View file

@ -338,14 +338,14 @@ ggml_fp16_t ggml_fp32_to_fp16(float x) {
return GGML_FP32_TO_FP16(x);
}
void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int n) {
for (int i = 0; i < n; i++) {
void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int64_t n) {
for (int64_t i = 0; i < n; i++) {
y[i] = GGML_FP16_TO_FP32(x[i]);
}
}
void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int n) {
int i = 0;
void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int64_t n) {
int64_t i = 0;
#if defined(__F16C__)
for (; i + 7 < n; i += 8) {
__m256 x_vec = _mm256_loadu_ps(x + i);
@ -20311,11 +20311,11 @@ size_t ggml_quantize_chunk(
enum ggml_type type,
const float * src,
void * dst,
int start,
int nrows,
int n_per_row,
int64_t start,
int64_t nrows,
int64_t n_per_row,
const float * imatrix) {
const int n = nrows * n_per_row;
const int64_t n = (int64_t) nrows * n_per_row;
if (ggml_quantize_requires_imatrix(type)) {
GGML_ASSERT(imatrix != NULL);