root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Bump memory buffer

Browse Source
This commit is contained in:
Georgi Gerganov 2023-03-11 12:44:21 +02:00
parent 0c6803321c
commit 7d9ed7b25f
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
main.cpp
View File

@ -529,7 +529,7 @@ bool llama_eval(
const int d_key = n_embd/n_head; const int d_key = n_embd/n_head;
static size_t buf_size = 256u*1024*1024; static size_t buf_size = 512u*1024*1024;
static void * buf = malloc(buf_size); static void * buf = malloc(buf_size);
if (mem_per_token > 0 && mem_per_token*N > buf_size) { if (mem_per_token > 0 && mem_per_token*N > buf_size) {