diff --git a/vllm/platforms/cpu.py b/vllm/platforms/cpu.py
index 0b16a8e1d1d8..fe258f76b9d7 100644
--- a/vllm/platforms/cpu.py
+++ b/vllm/platforms/cpu.py
@@ -268,7 +268,7 @@ class CpuPlatform(Platform):
                 DEFAULT_MAX_NUM_BATCHED_TOKENS)
 
     @classmethod
-    def get_allowed_cpu_memory_node_list(
+    def get_allowed_cpu_core_node_list(
             cls) -> tuple[list[int], list[LogicalCPUInfo]]:
         assert platform.system() == "Linux"
 
diff --git a/vllm/v1/worker/cpu_worker.py b/vllm/v1/worker/cpu_worker.py
index 2dc28d93049a..f83d6804840e 100644
--- a/vllm/v1/worker/cpu_worker.py
+++ b/vllm/v1/worker/cpu_worker.py
@@ -132,7 +132,7 @@ class CPUWorker(Worker):
         """
 
         allowed_numa_nodes, logical_cpu_list = \
-            CpuPlatform.get_allowed_cpu_memory_node_list()
+            CpuPlatform.get_allowed_cpu_core_node_list()
         assert len(allowed_numa_nodes) >= self.parallel_config.world_size, (
             f"No enough allowed NUMA nodes to bind threads of "
             f"{self.parallel_config.world_size} CPUWorkers. "