diff --git a/vllm/config.py b/vllm/config.py
index 508cdfaec1c4..ce7e2a2929cf 100644
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -1506,6 +1506,8 @@ class CacheConfig:
     """This enables dynamic calculation of `k_scale` and `v_scale` when
     kv_cache_dtype is fp8. If `False`, the scales will be loaded from the model
     checkpoint if available. Otherwise, the scales will default to 1.0."""
+    cpu_kvcache_space_bytes: Optional[int] = None
+    """(CPU backend only) CPU key-value cache space."""
 
     # Will be set after profiling.
     num_gpu_blocks: Optional[int] = field(default=None, init=False)