[https://nvbugs/5542867][fix] Fix the non-determinism issue in the mm_encoder test (#8033)

Signed-off-by: Chang Liu (Enterprise Products) <[email protected]>

Author: chang-l

tests/unittest/_torch/multimodal/test_mm_encoder_standalone.py

@@ -168,7 +168,6 @@ def test_single_image_chat(model_key, multimodal_model_config):
     "llava-v1.6-mistral-7b-hf",
 ])
 def test_multi_request_batch_chat(model_key, multimodal_model_config):
-    pytest.skip("https://nvbugspro.nvidia.com/bug/5542867")
     """Test batching multiple multimodal requests and verify encoder path matches raw path.
 
     This mirrors test_single_image_chat but with a batch of size 3.
@@ -200,10 +199,12 @@ def test_multi_request_batch_chat(model_key, multimodal_model_config):
 
     encoder = MultimodalEncoder(model=encoder_model_dir,
                                 max_batch_size=max_batch_size)
-    llm = LLM(model=encoder_model_dir,
-              backend='pytorch',
-              kv_cache_config=kv_cache_config,
-              trust_remote_code=True)
+    llm = LLM(
+        model=encoder_model_dir,
+        backend='pytorch',
+        kv_cache_config=kv_cache_config,
+        max_batch_size=1,  # fix batch size to reduce non-determinism in tests
+        trust_remote_code=True)
 
     config_path = os.path.join(llm._hf_model_dir, 'config.json')
     assert os.path.exists(