vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixed compile error: GGML_BACKEND_TYPE_GPU (+1 squashed commits)

Browse source 
Squashed commits:

[00ca282a] fixed compile error: LLAMA_SPLIT_MODE_ROW
This commit is contained in:
Concedo 2024-02-26 10:49:02 +08:00
parent 3ccaf8e09a
commit d47e13c892
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -2863,7 +2863,7 @@ struct llama_model_loader {
bool shouldoffload = (layernum>=0 && clblast_offload_fallback_layers>layernum);
if(shouldoffload)
{
cur->backend = GGML_BACKEND_GPU;
cur->backend = GGML_BACKEND_TYPE_GPU;
ggml_cl_transform_tensor(cur->data, cur);
}
}