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

Fix crash for 65B model with pre-allocated memory (#485)

Browse source
This commit is contained in:
Chris Kuehl 2023-03-24 23:38:14 -05:00 committed by GitHub
parent 8520fc310e
commit 6f1ee4b640
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
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

@ -239,7 +239,7 @@ static bool kv_cache_init(
const int n_mem = n_layer*n_ctx;
const int n_elements = n_embd*n_mem;
cache.buf.resize(2*n_elements*ggml_type_size(wtype) + 2u*MB);
cache.buf.resize(2u*n_elements*ggml_type_size(wtype) + 2u*MB);
struct ggml_init_params params;
params.mem_size = cache.buf.size();