diff --git a/src/llama-kv-cache.cpp b/src/llama-kv-cache.cpp
index 02251cc74c..b06723634c 100644
--- a/src/llama-kv-cache.cpp
+++ b/src/llama-kv-cache.cpp
@@ -12,7 +12,6 @@
 #include <limits>
 #include <map>
 #include <stdexcept>
-#include <unordered_map>
 
 static bool ggml_is_power_of_2(int n) {
     return (n & (n - 1)) == 0;
@@ -2670,7 +2669,3 @@ void llama_kv_cache_context::set_input_k_rot(ggml_tensor * dst) const {
 void llama_kv_cache_context::set_input_v_rot(ggml_tensor * dst) const {
     kv->set_input_v_rot(dst);
 }
-
-void llama_kv_cache_context::get_prev_tokens(const llama_ubatch & ubatch, uint32_t n, std::vector<llama_token> & res) const {
-    kv->get_prev_tokens(ubatch, n, res);
-}
diff --git a/src/llama-kv-cache.h b/src/llama-kv-cache.h
index 4ef6b9b4e2..62ce374e0d 100644
--- a/src/llama-kv-cache.h
+++ b/src/llama-kv-cache.h
@@ -404,9 +404,6 @@ public:
     void set_input_k_rot(ggml_tensor * dst) const;
     void set_input_v_rot(ggml_tensor * dst) const;
 
-    // see llama_kv_cache::get_prev_tokens()
-    void get_prev_tokens(const llama_ubatch & ubatch, uint32_t n, std::vector<llama_token> & res) const;
-
 private:
     llama_memory_status status;