mtmd, model: allow skip build_vit() (#24077)

* add model

* nits

src/llama-arch.cpp

@@ -329,6 +329,7 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
     { LLM_KV_TOKENIZER_FIM_PAD_ID,           "tokenizer.ggml.fim_pad_token_id"         },
     { LLM_KV_TOKENIZER_FIM_REP_ID,           "tokenizer.ggml.fim_rep_token_id"         },
     { LLM_KV_TOKENIZER_FIM_SEP_ID,           "tokenizer.ggml.fim_sep_token_id"         },
+    { LLM_KV_TOKENIZER_SUPPRESS_TOKENS,      "tokenizer.ggml.suppress_tokens"          },
 
     { LLM_KV_ADAPTER_TYPE,                    "adapter.type"               },
     { LLM_KV_ADAPTER_LORA_ALPHA,              "adapter.lora.alpha"         },

src/llama-arch.h

@@ -318,6 +318,7 @@ enum llm_kv {
     LLM_KV_TOKENIZER_FIM_PAD_ID,
     LLM_KV_TOKENIZER_FIM_REP_ID,
     LLM_KV_TOKENIZER_FIM_SEP_ID,
+    LLM_KV_TOKENIZER_SUPPRESS_TOKENS,
 
     LLM_KV_ADAPTER_TYPE,
     LLM_KV_ADAPTER_LORA_ALPHA,

src/llama-vocab.cpp

@@ -1815,6 +1815,8 @@ struct llama_vocab::impl {
     // set of all tokens that cause "end of generation"
     std::set<llama_token> special_eog_ids;
 
+    std::vector<llama_token> suppress_tokens;
+
     std::unique_ptr<llm_tokenizer> tokenizer;
 
     std::vector<char> precompiled_charsmap;
@@ -2533,6 +2535,16 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
         // Lowercase normalizer flag (consulted by WPM / whitespace BPE)
         ml.get_key(LLM_KV_TOKENIZER_NORMALIZER_LOWERCASE, normalizer_lowercase, false);
 
+        // suppress tokens
+        {
+            const int suppress_idx = gguf_find_key(ctx, kv(LLM_KV_TOKENIZER_SUPPRESS_TOKENS).c_str());
+            if (suppress_idx != -1) {
+                const int n = gguf_get_arr_n(ctx, suppress_idx);
+                const int32_t * data = (const int32_t *) gguf_get_arr_data(ctx, suppress_idx);
+                suppress_tokens.assign(data, data + n);
+            }
+        }
+
         // auto-detect special tokens by text
         // TODO: convert scripts should provide these tokens through the KV metadata LLM_KV_TOKENIZER_...
         //       for now, we apply this workaround to find the tokens based on their text
@@ -3961,6 +3973,10 @@ bool llama_vocab::get_normalizer_lowercase() const {
     return pimpl->normalizer_lowercase;
 }
 
+const std::vector<llama_token> & llama_vocab::get_suppress_tokens() const {
+    return pimpl->suppress_tokens;
+}
+
 int llama_vocab::max_token_len() const {
     return pimpl->max_token_len;
 }

src/llama-vocab.h

@@ -143,6 +143,8 @@ struct llama_vocab {
     bool get_treat_whitespace_as_suffix() const;
     bool get_normalizer_lowercase      () const;
 
+    const std::vector<llama_token> & get_suppress_tokens() const;
+
     int max_token_len() const;
 
     int find_bpe_rank(const std::string & token_left, const std::string & token_right) const;

src/models/gemma4.cpp

@@ -142,6 +142,31 @@ static ggml_tensor * ggml_view_2d_slice(ggml_context * ctx0, ggml_tensor * x, in
                         idx * x->ne[0] * x->ne[1] * ggml_element_size(x));
 }
 
+// TODO @ngxson : maybe improve this in the future
+class llm_graph_input_logits_bias : public llm_graph_input_i {
+public:
+    llm_graph_input_logits_bias(const llama_vocab & vocab) {
+        arr.resize(vocab.n_tokens(), 0.0f);
+        for (llama_token id : vocab.get_suppress_tokens()) {
+            if (0 <= id && id < (int32_t)vocab.n_tokens()) {
+                arr[id] = -INFINITY;
+            }
+        }
+    }
+    virtual ~llm_graph_input_logits_bias() = default;
+
+    void set_input(const llama_ubatch *) override {
+        const int64_t n_vocab = arr.size();
+        ggml_backend_tensor_set(logits_bias, arr.data(), 0, n_vocab*ggml_element_size(logits_bias));
+    }
+
+    // bool can_reuse(const llm_graph_params & params) override;
+
+    ggml_tensor * logits_bias = nullptr; // F32 [n_vocab]
+
+    std::vector<float> arr;
+};
+
 llama_model_gemma4::graph::graph(const llama_model & model, const llm_graph_params & params) :
         llm_graph_context(params),
         model(model),
@@ -388,6 +413,16 @@ llama_model_gemma4::graph::graph(const llama_model & model, const llm_graph_para
         cur = ggml_scale(ctx0, cur, hparams.f_final_logit_softcapping);
     }
 
+    // apply logits bias if needed (e.g. for gemma4_unified patch)
+    // this is to mirror the suppress_tokens patch on transformers, to avoid model from outputing <image|> and <audio|> tokens (which is a known issue related to the checkpoint)
+    // TODO: maybe handle this inside the sampling system in the future
+    if (!model.vocab.get_suppress_tokens().empty()) {
+        auto inp_bias = std::make_unique<llm_graph_input_logits_bias>(model.vocab);
+        inp_bias->logits_bias = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, inp_bias->arr.size());
+        cur = ggml_add(ctx0, cur, inp_bias->logits_bias);
+        res->add_input(std::move(inp_bias));
+    }
+
     cb(cur, "result_output", -1);
     res->t_logits = cur;