wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-09 07:16:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

model : fix llama_model::n_gpu_layers() (#24188)

Browse Source
This commit is contained in:
Georgi Gerganov
2026-06-05 17:11:42 +03:00
committed by GitHub
parent 2016bf2b3b
commit 96fbe00393
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+2 -1
View File
@@ -1636,7 +1636,8 @@ const float * llama_model::tensor_split() const {
}
uint32_t llama_model::n_gpu_layers() const {
return params.n_gpu_layers >= 0 ? params.n_gpu_layers : hparams.n_layer() + 1;
// note: plus 1 for the "output" layer
return params.n_gpu_layers >= 0 ? params.n_gpu_layers : hparams.n_layer_all + 1;
}
llama_split_mode llama_model::split_mode() const {