vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-09 15:44:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add speculative decoding support to the server and command-line interfaces

Browse source
This commit is contained in:
DeEMO 2025-06-23 20:36:32 +08:00 • committed by DeEMO
parent 3a03549fed
commit ea3ebcbca2
11 changed files with 591 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -3107,7 +3107,7 @@ void yaml_dump_non_result_info(FILE * stream, const gpt_params & params, const l
fprintf(stream, "mirostat_lr: %f # default: 0.1\n", sparams.mirostat_eta);
fprintf(stream, "mlock: %s # default: false\n", params.use_mlock ? "true" : "false");
fprintf(stream, "model: %s # default: %s\n", params.model.c_str(), DEFAULT_MODEL_PATH);
fprintf(stream, "model_draft: %s # default:\n", params.model_draft.c_str());
fprintf(stream, "model_draft: %s # default:\n", params.speculative.model.c_str());
fprintf(stream, "multiline_input: %s # default: false\n", params.multiline_input ? "true" : "false");
fprintf(stream, "n_gpu_layers: %d # default: -1\n", params.n_gpu_layers);
fprintf(stream, "n_predict: %d # default: -1 (unlimited)\n", params.n_predict);