diff --git a/FlagEmbedding/inference/embedder/decoder_only/base.py b/FlagEmbedding/inference/embedder/decoder_only/base.py
index 2912ca05..647637f3 100644
--- a/FlagEmbedding/inference/embedder/decoder_only/base.py
+++ b/FlagEmbedding/inference/embedder/decoder_only/base.py
@@ -257,7 +257,7 @@ def encode_single_device(
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         # encode
diff --git a/FlagEmbedding/inference/embedder/decoder_only/icl.py b/FlagEmbedding/inference/embedder/decoder_only/icl.py
index 1206b8a4..5ec87e9e 100644
--- a/FlagEmbedding/inference/embedder/decoder_only/icl.py
+++ b/FlagEmbedding/inference/embedder/decoder_only/icl.py
@@ -409,7 +409,7 @@ def encode_queries_single_device(
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         # encode
@@ -519,7 +519,7 @@ def encode_single_device(
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         # encode
diff --git a/FlagEmbedding/inference/embedder/encoder_only/base.py b/FlagEmbedding/inference/embedder/encoder_only/base.py
index 6b27ec14..0cc8b76c 100644
--- a/FlagEmbedding/inference/embedder/encoder_only/base.py
+++ b/FlagEmbedding/inference/embedder/encoder_only/base.py
@@ -238,7 +238,7 @@ def encode_single_device(
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         # encode
diff --git a/FlagEmbedding/inference/embedder/encoder_only/m3.py b/FlagEmbedding/inference/embedder/encoder_only/m3.py
index 42c207d7..d5ea28d4 100644
--- a/FlagEmbedding/inference/embedder/encoder_only/m3.py
+++ b/FlagEmbedding/inference/embedder/encoder_only/m3.py
@@ -406,7 +406,7 @@ def _process_colbert_vecs(colbert_vecs: np.ndarray, attention_mask: list):
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         # encode
diff --git a/FlagEmbedding/inference/reranker/decoder_only/base.py b/FlagEmbedding/inference/reranker/decoder_only/base.py
index b50a697e..a8bd5b85 100644
--- a/FlagEmbedding/inference/reranker/decoder_only/base.py
+++ b/FlagEmbedding/inference/reranker/decoder_only/base.py
@@ -412,7 +412,7 @@ def compute_score_single_gpu(
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         dataset, dataloader = None, None
diff --git a/FlagEmbedding/inference/reranker/decoder_only/layerwise.py b/FlagEmbedding/inference/reranker/decoder_only/layerwise.py
index 8e50271f..63f45c9f 100644
--- a/FlagEmbedding/inference/reranker/decoder_only/layerwise.py
+++ b/FlagEmbedding/inference/reranker/decoder_only/layerwise.py
@@ -282,7 +282,7 @@ def compute_score_single_gpu(
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         dataset, dataloader = None, None
diff --git a/FlagEmbedding/inference/reranker/decoder_only/lightweight.py b/FlagEmbedding/inference/reranker/decoder_only/lightweight.py
index a9bea311..0acdc1f4 100644
--- a/FlagEmbedding/inference/reranker/decoder_only/lightweight.py
+++ b/FlagEmbedding/inference/reranker/decoder_only/lightweight.py
@@ -368,7 +368,7 @@ def compute_score_single_gpu(
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         all_scores = []
diff --git a/FlagEmbedding/inference/reranker/encoder_only/base.py b/FlagEmbedding/inference/reranker/encoder_only/base.py
index 9af0b2d8..eb98c737 100644
--- a/FlagEmbedding/inference/reranker/encoder_only/base.py
+++ b/FlagEmbedding/inference/reranker/encoder_only/base.py
@@ -169,7 +169,7 @@ def compute_score_single_gpu(
                 flag = True
             except RuntimeError as e:
                 batch_size = batch_size * 3 // 4
-            except torch.OutofMemoryError as e:
+            except torch.cuda.OutOfMemoryError as e:
                 batch_size = batch_size * 3 // 4
 
         all_scores = []