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

2025-06-30 09:35:35 +00:00
parent 1ea2d61a97
commit 2e8e42a5ad
11 changed files with 591 additions and 31 deletions
@@ -3111,7 +3111,7 @@ 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);