Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix typos

Browse Source
This commit is contained in:
Concedo
2023-07-03 21:36:42 +08:00
parent 3d2907d208
commit bfeb3471d7
3 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
otherarch/mpt_v3.cpp
+2 -2
View File
@@ -301,7 +301,7 @@ bool mpt_model_load(const std::string & fname, mpt_model & model, gpt_vocab & vo
const auto & hparams = model.hparams;
size_t vram_total = 0;
const int n_gpu = std::min(gpulayers, int(hparams.n_layers));
fprintf(stderr, "%s: [opencl] offloading %d layers to GPU\n", __func__, n_gpu);
fprintf(stderr, "%s: [GPU] offloading %d layers to GPU\n", __func__, n_gpu);
for (int i = 0; i < n_gpu; ++i) {
const auto & layer = model.layers[i];
layer.ffn_up_proj->backend = GGML_BACKEND_GPU;
@@ -320,7 +320,7 @@ bool mpt_model_load(const std::string & fname, mpt_model & model, gpt_vocab & vo
ggml_cuda_transform_tensor(layer.c_attn_out_proj_weight->data,layer.c_attn_out_proj_weight); vram_total += ggml_nbytes(layer.c_attn_out_proj_weight);
#endif
}
fprintf(stderr, "%s: [opencl] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
fprintf(stderr, "%s: [GPU] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
}
#endif