root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 03:44:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

fixup! Store layers in VRAM

Browse Source
This commit is contained in:
JohannesGaessler 2023-05-11 07:05:52 +02:00
parent 3ed4588e22
commit 8a9d7ce624
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/common.cpp
View File

@ -412,7 +412,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
if (llama_mmap_supported()) { if (llama_mmap_supported()) {
fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n"); fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
} }
fprintf(stderr, " --gpu_layers number of layers to store in VRAM"); fprintf(stderr, " --gpu_layers number of layers to store in VRAM\n");
fprintf(stderr, " --mtest compute maximum memory usage\n"); fprintf(stderr, " --mtest compute maximum memory usage\n");
fprintf(stderr, " --verbose-prompt print prompt before generation\n"); fprintf(stderr, " --verbose-prompt print prompt before generation\n");
fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n"); fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n");