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

Increase 3B scratch buffers. (#1698)

Browse Source 
The 128 MB was too optimistic.
Too bad it is not dynamically computed.
This commit is contained in:
Henri Vasserman
2023-06-05 13:43:08 +03:00
committed by GitHub
parent d1f563a743
commit 5220a991a5
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

@@ -63,7 +63,7 @@ static const size_t MB = 1024*1024;
static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0() static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0()
{ {
static std::map<e_model, size_t> k_sizes = { static std::map<e_model, size_t> k_sizes = {
{ MODEL_3B, 128ull * MB }, { MODEL_3B, 256ull * MB },
{ MODEL_7B, 512ull * MB }, { MODEL_7B, 512ull * MB },
{ MODEL_13B, 512ull * MB }, { MODEL_13B, 512ull * MB },
{ MODEL_30B, 512ull * MB }, { MODEL_30B, 512ull * MB },
@@ -75,7 +75,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH0()
static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1() static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1()
{ {
static std::map<e_model, size_t> k_sizes = { static std::map<e_model, size_t> k_sizes = {
{ MODEL_3B, 128ull * MB }, { MODEL_3B, 256ull * MB },
{ MODEL_7B, 512ull * MB }, { MODEL_7B, 512ull * MB },
{ MODEL_13B, 512ull * MB }, { MODEL_13B, 512ull * MB },
{ MODEL_30B, 512ull * MB }, { MODEL_30B, 512ull * MB },