fix: Remove llama_model_is_hybrid_Recurrent public API

#13979 (comment)

Branch: HybridRecurrentCache

Signed-off-by: Gabe Goodhart <[email protected]>

Author: gabe-l-hart

include/llama.h

@@ -572,9 +572,6 @@ extern "C" {
     // Returns true if the model is recurrent (like Mamba, RWKV, etc.)
     LLAMA_API bool llama_model_is_recurrent(const struct llama_model * model);
 
-    // Returns true if the model is hybrid-recurrent (like Jamba, Bamba, etc.)
-    LLAMA_API bool llama_model_is_hybrid_recurrent(const struct llama_model * model);
-
     // Returns 0 on success
     LLAMA_API uint32_t llama_model_quantize(
             const char * fname_inp,

src/llama-model.cpp

@@ -14405,10 +14405,6 @@ bool llama_model_is_recurrent(const llama_model * model) {
     return llm_arch_is_recurrent(model->arch);
 }
 
-bool llama_model_is_hybrid_recurrent(const llama_model * model) {
-    return llm_arch_is_hybrid_recurrent(model->arch);
-}
-
 const std::vector<std::pair<std::string, ggml_tensor *>> & llama_internal_get_tensor_map(const llama_model * model) {
     return model->tensors_by_name;
 }