diff --git a/fastdeploy/worker/gpu_model_runner.py b/fastdeploy/worker/gpu_model_runner.py
index 7ff93415aad..c150f43e72e 100644
--- a/fastdeploy/worker/gpu_model_runner.py
+++ b/fastdeploy/worker/gpu_model_runner.py
@@ -3650,7 +3650,7 @@ def _get_prompt_logprobs_list(
                 continue
             offset = self.share_inputs["cu_seqlens_q"][batch_id]
             prompt_hidden_states = hidden_states[offset : offset + num_logits]
-            logits = self.model.compute_logits(prompt_hidden_states)
+            logits = self.model.compute_logits(prompt_hidden_states, self.forward_meta)
             prompt_token_ids = request.prompt_token_ids[start_tok : start_tok + num_logits]
             prompt_token_ids_tensor = paddle.to_tensor(prompt_token_ids, dtype="int64")
             if logprobs_mode == "raw_logprobs":
diff --git a/tests/worker/test_gpu_prompt_logprobs.py b/tests/worker/test_gpu_prompt_logprobs.py
index f12bc4cf3dc..cc4e0120a8b 100644
--- a/tests/worker/test_gpu_prompt_logprobs.py
+++ b/tests/worker/test_gpu_prompt_logprobs.py
@@ -20,6 +20,7 @@
 
 import numpy as np
 import paddle
+from utils import MockForwardMeta
 
 from fastdeploy.config import (
     CacheConfig,
@@ -104,7 +105,7 @@ def __init__(self, vocab_size=128, hidden_size=128):
         self.hidden_size = hidden_size
         self.weight = paddle.rand([hidden_size, vocab_size], dtype="float32")
 
-    def compute_logits(self, x):
+    def compute_logits(self, x, forward_meta=None):
         return paddle.matmul(x.astype("float32"), self.weight)
 
 
@@ -175,6 +176,7 @@ def setup_model_runner(self):
         model_runner.model = FakeModel(cfg.model_config.vocab_size, cfg.model_config.hidden_size)
 
         model_runner.in_progress_prompt_logprobs = {}
+        model_runner.forward_meta = MockForwardMeta()
 
         return model_runner