CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix integer overflow during quantization (#6063)

Browse Source
This commit is contained in:
Georgi Gerganov
2024-03-14 22:58:41 +02:00
committed by GitHub
parent 6e0438da3c
commit 4755afd1cb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@@ -11977,7 +11977,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
return new_type;
}
static int32_t llama_tensor_quantize_internal(enum ggml_type new_type, const float * f32_data, void * new_data, const int chunk_size, int nrows, int n_per_row, const float * imatrix, std::vector<std::thread> & workers, const int nthread) {
static size_t llama_tensor_quantize_internal(enum ggml_type new_type, const float * f32_data, void * new_data, const int chunk_size, int nrows, int n_per_row, const float * imatrix, std::vector<std::thread> & workers, const int nthread) {
std::mutex mutex;
int counter = 0;
size_t new_size = 0;