CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : increase scratch buffer size for 65B (ref #1152)

Browse Source 
Temporary solution
This commit is contained in:
Georgi Gerganov
2023-04-24 18:47:03 +03:00
parent 9b0a4d4214
commit 957c8ae21d
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama.cpp
View File

@@ -54,7 +54,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0()
{ MODEL_7B, 512ull * MB }, { MODEL_7B, 512ull * MB },
{ MODEL_13B, 512ull * MB }, { MODEL_13B, 512ull * MB },
{ MODEL_30B, 512ull * MB }, { MODEL_30B, 512ull * MB },
{ MODEL_65B, 512ull * MB }, { MODEL_65B, 1024ull * MB },
}; };
return _MEM_REQ_SCRATCH0; return _MEM_REQ_SCRATCH0;
} }
@@ -65,7 +65,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1()
{ MODEL_7B, 512ull * MB }, { MODEL_7B, 512ull * MB },
{ MODEL_13B, 512ull * MB }, { MODEL_13B, 512ull * MB },
{ MODEL_30B, 512ull * MB }, { MODEL_30B, 512ull * MB },
{ MODEL_65B, 512ull * MB }, { MODEL_65B, 1024ull * MB },
}; };
return _MEM_REQ_SCRATCH1; return _MEM_REQ_SCRATCH1;
} }