aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-11-09 15:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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;
static size_t buf_size = 256u*1024*1024;
static size_t buf_size = 512u*1024*1024;
static void * buf = malloc(buf_size);
if (mem_per_token > 0 && mem_per_token*N > buf_size) {