diff --git a/vllm/model_executor/models/whisper.py b/vllm/model_executor/models/whisper.py
index b8512b735da94..15e35fa9cd2c9 100644
--- a/vllm/model_executor/models/whisper.py
+++ b/vllm/model_executor/models/whisper.py
@@ -743,7 +743,7 @@ def _create_fake_bias_for_k_proj(
     So that the bias for k_proj in qkv_proj can be initialized with zeros.
     """
     for name, weight in weights:
-        if ".self_attn.k_proj.weight" in name:
+        if name.endswith(".self_attn.k_proj.weight"):
             bias = torch.zeros(weight.size(0))
             bias_name = name.replace("weight", "bias")
             yield from [(name, weight), (bias_name, bias)]