llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520)

This matches how it is done for logit_bias and mirostat samplers, see https://github.com/ggml-org/llama.cpp/pull/25262#discussion_r3703951151
2026-08-04 09:02:49 +03:00
parent 22dc605c4e
commit 935cad6497
6 changed files with 16 additions and 13 deletions
@@ -383,7 +383,7 @@ struct common_sampler * common_sampler_init(
                    samplers.push_back(llama_sampler_init_infill(vocab));
                    break;
                case COMMON_SAMPLER_TYPE_PENALTIES:
-                    samplers.push_back(llama_sampler_init_penalties(params.penalty_last_n, params.penalty_repeat, params.penalty_freq, params.penalty_present));
+                    samplers.push_back(llama_sampler_init_penalties(llama_vocab_n_tokens(vocab), params.penalty_last_n, params.penalty_repeat, params.penalty_freq, params.penalty_present));
                    break;
                case COMMON_SAMPLER_TYPE_ADAPTIVE_P:
                    // the `adaptive-p` sampler is like `dist` and `mirostat` in that it selects