diff --git a/fastdeploy/config.py b/fastdeploy/config.py
index b4bf00ceb1..d0af627470 100644
--- a/fastdeploy/config.py
+++ b/fastdeploy/config.py
@@ -2064,7 +2064,10 @@ class FDConfig:
 
         if self.scheduler_config.max_num_batched_tokens is None:
             if int(envs.ENABLE_V1_KVCACHE_SCHEDULER):
-                self.scheduler_config.max_num_batched_tokens = 8192  # if set to max_model_len, it's easy to be OOM
+                if int(envs.FD_DISABLE_CHUNKED_PREFILL):
+                    self.scheduler_config.max_num_batched_tokens = self.model_config.max_model_len
+                else:
+                    self.scheduler_config.max_num_batched_tokens = 8192  # if set to max_model_len, it's easy to be OOM
             else:
                 if self.cache_config.enable_chunked_prefill:
                     self.scheduler_config.max_num_batched_tokens = 2048
diff --git a/fastdeploy/engine/args_utils.py b/fastdeploy/engine/args_utils.py
index 069fdfbf9d..1a275b59bd 100644
--- a/fastdeploy/engine/args_utils.py
+++ b/fastdeploy/engine/args_utils.py
@@ -1498,7 +1498,11 @@ class EngineArgs:
 
         if self.max_num_batched_tokens is None:
             if int(envs.ENABLE_V1_KVCACHE_SCHEDULER):
-                if current_platform.is_maca() or current_platform.is_iluvatar():
+                if (
+                    int(envs.FD_DISABLE_CHUNKED_PREFILL)
+                    or current_platform.is_maca()
+                    or current_platform.is_iluvatar()
+                ):
                     self.max_num_batched_tokens = self.max_model_len
                 else:
                     self.max_num_batched_tokens = 8192  # if set to max_model_len, it's easy to be OOM