diff --git a/vllm/model_executor/models/deepseek_v2.py b/vllm/model_executor/models/deepseek_v2.py
index 773f5abe71da..fb6725c9abc3 100644
--- a/vllm/model_executor/models/deepseek_v2.py
+++ b/vllm/model_executor/models/deepseek_v2.py
@@ -592,7 +592,8 @@ def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
             self.embed_tokens = VocabParallelEmbedding(
                 config.vocab_size,
                 config.hidden_size,
-            )
+                quant_config=quant_config,
+                prefix=f"{prefix}.embed_tokens")
         else:
             self.embed_tokens = PPMissingLayer()