diff --git a/backend/cpp/llama-cpp/grpc-server.cpp b/backend/cpp/llama-cpp/grpc-server.cpp
index 46066202ea38..386aa78d05f5 100644
--- a/backend/cpp/llama-cpp/grpc-server.cpp
+++ b/backend/cpp/llama-cpp/grpc-server.cpp
@@ -291,6 +291,11 @@ static void params_parse(server_context& ctx_server, const backend::ModelOptions
         }
     }
 
+    if (!params.kv_overrides.empty()) {
+        params.kv_overrides.emplace_back();
+        params.kv_overrides.back().key[0] = 0;
+    }
+
     // TODO: Add yarn
 
     if (!request->tensorsplit().empty()) {
diff --git a/docs/content/docs/advanced/advanced-usage.md b/docs/content/docs/advanced/advanced-usage.md
index 8feaf95188ca..77e6ef63efc4 100644
--- a/docs/content/docs/advanced/advanced-usage.md
+++ b/docs/content/docs/advanced/advanced-usage.md
@@ -233,6 +233,15 @@ n_draft: 0
 # Quantization settings for the model, impacting memory and processing speed.
 quantization: ""
 
+# List of KV Overrides for llama.cpp (--override-kv flag)
+# Format: KEY=TYPE:VALUE
+# Example: `qwen3moe.expert_used_count=int:10`
+# Use this to override model configuration values at runtime.
+# Supported types include: int, float, string, bool.
+# Multiple overrides can be specified as a list.
+overrides:
+  - KEY=TYPE:VALUE
+
 # Utilization percentage of GPU memory to allocate for the model. (vLLM)
 gpu_memory_utilization: 0