haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests 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
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 2 additions and 2 deletions
Show stats 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_13B, 512ull * MB },
{ MODEL_30B, 512ull * MB },
{ MODEL_65B, 512ull * MB },
{ MODEL_65B, 1024ull * MB },
};
return _MEM_REQ_SCRATCH0;
}
@ -65,7 +65,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1()
{ MODEL_7B, 512ull * MB },
{ MODEL_13B, 512ull * MB },
{ MODEL_30B, 512ull * MB },
{ MODEL_65B, 512ull * MB },
{ MODEL_65B, 1024ull * MB },
};
return _MEM_REQ_SCRATCH1;
}