Skip to content

Commit

Permalink
Update speculative_decoding_lm.cpp
Browse files Browse the repository at this point in the history
  • Loading branch information
iefode authored Jan 17, 2025
1 parent 075245e commit c440e08
Showing 1 changed file with 2 additions and 0 deletions.
2 changes: 2 additions & 0 deletions samples/cpp/text_generation/speculative_decoding_lm.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@ int main(int argc, char* argv[]) try {
// Speculative decoding generation parameters like `num_assistant_tokens` and `assistant_confidence_threshold` are mutually excluded
// add parameter to enable speculative decoding to generate `num_assistant_tokens` candidates by draft_model per iteration
config.num_assistant_tokens = 5;
// add parameter to enable speculative decoding to generate candidates by draft_model while candidate probability is higher than `assistant_confidence_threshold`
// config.assistant_confidence_threshold = 0.4;

std::string main_model_path = argv[1];
std::string draft_model_path = argv[2];
Expand Down

0 comments on commit c440e08

Please sign in to comment.