CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
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

@@ -632,7 +632,7 @@ static bool llama_eval_internal(
auto & mem_per_token = lctx.mem_per_token; auto & mem_per_token = lctx.mem_per_token;
// TODO: fix this hardcoded size // 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); 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) {