aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-11-12 16:29:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Temporary bump the memory buffer size - hopefully fix issues from 483bab2e

Browse source
This commit is contained in:
Georgi Gerganov 2023-03-24 18:23:56 +02:00
parent f4f5362edb
commit 31572d9665
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
llama.cpp
View file

@ -632,7 +632,7 @@ static bool llama_eval_internal(
auto & mem_per_token = lctx.mem_per_token;
// TODO: fix this hardcoded size
static size_t buf_size = 512u*1024*1024;
static size_t buf_size = 2048u*1024*1024; // TMP !!!
static void * buf = malloc(buf_size);
if (mem_per_token > 0 && mem_per_token*N > buf_size) {