common : print --flash-attn in help
This commit is contained in:
parent
871fcb6e10
commit
a39217d428
1 changed files with 1 additions and 0 deletions
|
@ -1482,6 +1482,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
|
||||||
printf(" -ns N, --sequences N number of sequences to decode (default: %d)\n", params.n_sequences);
|
printf(" -ns N, --sequences N number of sequences to decode (default: %d)\n", params.n_sequences);
|
||||||
printf(" -ps N, --p-split N speculative decoding split probability (default: %.1f)\n", (double)params.p_split);
|
printf(" -ps N, --p-split N speculative decoding split probability (default: %.1f)\n", (double)params.p_split);
|
||||||
printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: disabled)\n");
|
printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: disabled)\n");
|
||||||
|
printf(" -fa, --flash-attn enable Flash Attention (default: %s)\n", params.flash_attn ? "enabled" : "disabled");
|
||||||
printf(" --mmproj MMPROJ_FILE path to a multimodal projector file for LLaVA. see examples/llava/README.md\n");
|
printf(" --mmproj MMPROJ_FILE path to a multimodal projector file for LLaVA. see examples/llava/README.md\n");
|
||||||
printf(" --image IMAGE_FILE path to an image file. use with multimodal models\n");
|
printf(" --image IMAGE_FILE path to an image file. use with multimodal models\n");
|
||||||
if (llama_supports_mlock()) {
|
if (llama_supports_mlock()) {
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue