sleepy/llama.cpp
1
0
Fork 0
Code Issues 16 Pull Requests Actions 30 Packages Projects Releases Wiki Activity

llama: fix magic number of 999 for GPU layers (#18266)

Browse Source 
* llama: fix magic number of 999 for GPU layers

* use strings for -ngl, -ngld

* enacapsulate n_gpu_layers, split_mode
This commit is contained in:
Johannes Gäßler
2025-12-27 20:18:35 +01:00
committed by GitHub
parent 06705fdcb3
commit 026d2ad472
7 changed files with 46 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+1 -4
View File
@@ -1341,10 +1341,7 @@ struct llama_model_params common_model_params_to_llama(common_params & params) {
mparams.devices = params.devices.data();
}
if (params.n_gpu_layers != -1) {
mparams.n_gpu_layers = params.n_gpu_layers;
}
mparams.n_gpu_layers = params.n_gpu_layers;
mparams.main_gpu = params.main_gpu;
mparams.split_mode = params.split_mode;
mparams.tensor_split = params.tensor_split;