vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-13 10:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'master' into concedo

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
This commit is contained in:
Concedo 2023-04-22 16:22:08 +08:00
commit 1b7aa2b815
3 changed files with 14 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama.cpp
View file

@ -68,7 +68,7 @@ static const std::map<e_model, size_t> & MEM_REQ_SCRATCH1()
{ MODEL_65B, 512ull * MB },
};
return _MEM_REQ_SCRATCH1;
};
}
// 2*n_embd*n_ctx*n_layer*sizeof(float16)
static const std::map<e_model, size_t> & MEM_REQ_KV_SELF()
@ -80,7 +80,7 @@ static const std::map<e_model, size_t> & MEM_REQ_KV_SELF()
{ MODEL_65B, 5120ull * MB },
};
return _MEM_REQ_KV_SELF;
};
}
// this is mostly needed for temporary mul_mat buffers to dequantize the data
// not actually needed if BLAS is disabled
@ -93,7 +93,7 @@ static const std::map<e_model, size_t> & MEM_REQ_EVAL()
{ MODEL_65B, 1536ull * MB },
};
return _MEM_REQ_EVAL;
};
}
// default hparams (LLaMA 7B)
struct llama_hparams {