[Bugfix] Missing quant_config in deepseek embedding layer (#12836)

vllm/model_executor/models/deepseek_v2.py

@@ -581,7 +581,8 @@ class DeepseekV2Model(nn.Module):
             self.embed_tokens = VocabParallelEmbedding(
                 config.vocab_size,
                 config.hidden_size,
-            )
+                quant_config=quant_config,
+                prefix=f"{prefix}.embed_tokens")
         else:
             self.embed_tokens = PPMissingLayer()