Store layers in VRAM
This commit is contained in:
parent
d052a0ed4c
commit
3ed4588e22
8 changed files with 74 additions and 10 deletions
|
@ -68,6 +68,7 @@ struct gpt_params {
|
|||
bool perplexity = false; // compute perplexity over the prompt
|
||||
bool use_mmap = true; // use mmap for faster loads
|
||||
bool use_mlock = false; // use mlock to keep model in memory
|
||||
int gpu_layers = 0; // number of layers to store in VRAM
|
||||
bool mem_test = false; // compute maximum memory usage
|
||||
bool verbose_prompt = false; // print prompt tokens before generation
|
||||
};
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue