CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-15 11:17:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

speculative : add --draft CLI arg

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-03 13:51:07 +03:00
parent a15ca746c7
commit 847896aba7
3 changed files with 11 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/speculative/speculative.cpp
View File

@@ -84,7 +84,7 @@ int main(int argc, char ** argv) {
//GGML_ASSERT(n_vocab == llama_n_vocab(ctx_dft));
// how many tokens to draft each time
const int n_draft = 16;
const int n_draft = params.n_draft;
int n_predict = 0;
int n_drafted = 0;