CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

common : better n_gpu_layers assignment

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-04 22:14:22 +03:00
parent 323a9d3b8c
commit 23360b15b6
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
common/common.cpp
View File

@@ -702,7 +702,9 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
lparams.n_ctx = params.n_ctx; lparams.n_ctx = params.n_ctx;
lparams.n_batch = params.n_batch; lparams.n_batch = params.n_batch;
lparams.n_gpu_layers = params.n_gpu_layers != -1 ? params.n_gpu_layers : lparams.n_gpu_layers; if (params.n_gpu_layers != -1) {
lparams.n_gpu_layers = params.n_gpu_layers;
}
lparams.main_gpu = params.main_gpu; lparams.main_gpu = params.main_gpu;
lparams.tensor_split = params.tensor_split; lparams.tensor_split = params.tensor_split;
lparams.low_vram = params.low_vram; lparams.low_vram = params.low_vram;