diff --git a/tests/e2e/multigpu/test_fsdp2.py b/tests/e2e/multigpu/test_fsdp2.py
index e10456240..a70ff9aa7 100644
--- a/tests/e2e/multigpu/test_fsdp2.py
+++ b/tests/e2e/multigpu/test_fsdp2.py
@@ -423,6 +423,7 @@ class TestFSDP2:
 
         verify_training_success(temp_dir)
 
+    @pytest.mark.skip(reason="slow test w cu129 + torch 2.9.1 + py3.12")
     @require_torch_2_7_0
     def test_dpo_lora(self, temp_dir):
         cfg = DictDefault(
diff --git a/tests/test_tokenizers.py b/tests/test_tokenizers.py
index 114c2bea2..82cae9b4a 100644
--- a/tests/test_tokenizers.py
+++ b/tests/test_tokenizers.py
@@ -116,6 +116,7 @@ class TestTokenizers:
             tokenizer.decode([128041, 128042]) == "RANDOM_OVERRIDE_1RANDOM_OVERRIDE_2"
         )
 
+    @pytest.mark.skip("FIXME slow test sdist py3.11 + torch2.8.0")
     @enable_hf_offline
     def test_added_tokens_overrides_gemma3(self, temp_dir):
         cfg = DictDefault(