diff --git a/src/llama-graph.cpp b/src/llama-graph.cpp
index 211d37273e1..49c865e7fcf 100644
--- a/src/llama-graph.cpp
+++ b/src/llama-graph.cpp
@@ -75,6 +75,12 @@ void llm_graph_input_dspark_logsnr::set_input(const llama_ubatch * ubatch) {
     }
 }
 
+bool llm_graph_input_dspark_logsnr::can_reuse(const llm_graph_params & params) {
+    // v_feat is a function of n_tokens and n_seqs_unq, both already checked by
+    // llm_graph_params::allow_reuse, and of min/max_log_snr, fixed per model
+    return feat && feat->ne[1] == params.ubatch.n_tokens;
+}
+
 void llm_graph_input_embd::set_input(const llama_ubatch * ubatch) {
     if (ubatch->token) {
         const int64_t n_tokens = ubatch->n_tokens;
diff --git a/src/llama-graph.h b/src/llama-graph.h
index b8efa7f0e3b..492574f69a1 100644
--- a/src/llama-graph.h
+++ b/src/llama-graph.h
@@ -152,6 +152,8 @@ class llm_graph_input_dspark_logsnr : public llm_graph_input_i {
 
     void set_input(const llama_ubatch * ubatch) override;
 
+    bool can_reuse(const llm_graph_params & params) override;
+
     ggml_tensor * feat = nullptr; // F32 [128, n_tokens]
 
     std::vector<float> v_feat;