diff --git a/vllm/worker/hpu_enc_dec_model_runner.py b/vllm/worker/hpu_enc_dec_model_runner.py
index b45d0f542c24..d3dfaed0cefd 100644
--- a/vllm/worker/hpu_enc_dec_model_runner.py
+++ b/vllm/worker/hpu_enc_dec_model_runner.py
@@ -42,7 +42,7 @@
 class HpuModelAdapterEncoderDecoder(HpuModelAdapter):
 
     def __init__(self, model, vllm_config, layer_names, is_causal):
-        super().__init__(model, vllm_config, layer_names, False)
+        super().__init__(model, vllm_config, layer_names, is_causal)
 
         # We only wrap the language model in HPU graph because some Ops in
         # vision model will fallback to CPU and cause the graph building fail.
diff --git a/vllm/worker/hpu_worker.py b/vllm/worker/hpu_worker.py
index c3ef8b19892e..dcd7c9b87001 100755
--- a/vllm/worker/hpu_worker.py
+++ b/vllm/worker/hpu_worker.py
@@ -92,7 +92,6 @@ def __init__(
             ModelRunnerClass = HPUPoolingModelRunner
         elif is_encoder_decoder_model:
             ModelRunnerClass = HPUEncoderDecoderModelRunner
-            is_causal = False
         self.model_runner: HPUModelRunnerBase = ModelRunnerClass(
             vllm_config=vllm_config,
             kv_cache_dtype=self.cache_config.cache_dtype,