diff --git a/vllm/worker/hpu_model_runner.py b/vllm/worker/hpu_model_runner.py
index b3b6bb4749d..213c17e55d0 100755
--- a/vllm/worker/hpu_model_runner.py
+++ b/vllm/worker/hpu_model_runner.py
@@ -2761,7 +2761,6 @@ def warmup_graphs(self,
 
     def _warmup_multimodal_graph(self,
                                  kv_caches,
-                                 available_mem,
                                  starting_mem=0,
                                  total_batch_seq=0.001):
 
@@ -2775,11 +2774,6 @@ def _warmup_multimodal_graph(self,
             _, max_seq_len = self.bucketing_ctx.get_max_prompt_shape()
             seq_len = max_seq_len
             batch_seq = 1 * num_patches
-            # Graph memory usage is proportional to seq dimension in a batch
-            mem_estimate = batch_seq / total_batch_seq * total_mem
-            if mem_estimate >= available_mem:
-                captured_all = False
-                continue
             graphed_multimodal_bucket = num_patches
             if graphed_multimodal_bucket in self.graphed_multimodal_buckets:
                 continue
@@ -2797,7 +2791,6 @@ def _warmup_multimodal_graph(self,
 
             used_mem = align_workers(mem_prof.consumed_device_memory,
                                      torch.distributed.ReduceOp.MAX)
-            available_mem -= used_mem
             total_mem += used_mem
             total_batch_seq += batch_seq