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

Always initialize mm_addr and mm_length in llama_model

Browse source
This commit is contained in:
Slaren 2023-03-29 08:53:14 +02:00
parent baa529e9c0
commit 3f5f4286dd
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -150,8 +150,8 @@ struct llama_model {
std::vector<uint8_t> buf;
// model memory mapped file
void * mm_addr;
size_t mm_length;
void * mm_addr = NULL;
size_t mm_length = 0;
// tensors
int n_loaded;