mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
infill : add new example + extend server API (#3296)
* vvhg-code-infill (#1) * infill in separate example (#2) * reverted changes to main and added infill example * cleanup * naming improvement * make : add missing blank line * fix missing semicolon * brought infill up to current main code * cleanup --------- Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
This commit is contained in:
@@ -120,6 +120,7 @@ struct gpt_params {
|
||||
bool use_mlock = false; // use mlock to keep model in memory
|
||||
bool numa = false; // attempt optimizations that help on some NUMA systems
|
||||
bool verbose_prompt = false; // print prompt tokens before generation
|
||||
bool infill = false; // use infill mode
|
||||
};
|
||||
|
||||
bool gpt_params_parse(int argc, char ** argv, gpt_params & params);
|
||||
|
||||
Reference in New Issue
Block a user