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
@@ -1256,7 +1256,6 @@ extern "C" {
        struct ggml_tensor * probs;
        struct ggml_tensor * sampled;
        struct ggml_tensor * candidates;
-        int64_t              n_vocab;
    };

    // user code can implement the interface below in order to create custom llama_sampler
@@ -1425,6 +1424,7 @@ extern "C" {

    /// NOTE: Avoid using on the full vocabulary as searching for repeated tokens can become slow. For example, apply top-k or top-p sampling first.
    LLAMA_API struct llama_sampler * llama_sampler_init_penalties(
+                             int32_t   n_vocab,
                             int32_t   penalty_last_n,   // last n tokens to penalize (0 = disable penalty, -1 = context size)
                               float   penalty_repeat,   // must be > 0.0, 1.0 = disabled
                               float   penalty_freq,     // must be finite, 0.0 = disabled