[Core][5/N] Fully working chunked prefill e2e (#3884)

tests/distributed/test_basic_distributed_correctness.py

@@ -33,11 +33,16 @@ def test_models(
     dtype: str,
     max_tokens: int,
 ) -> None:
+
     hf_model = hf_runner(model, dtype=dtype)
     hf_outputs = hf_model.generate_greedy(example_prompts, max_tokens)
     del hf_model
 
-    vllm_model = vllm_runner(model, dtype=dtype, tensor_parallel_size=2)
+    vllm_model = vllm_runner(
+        model,
+        dtype=dtype,
+        tensor_parallel_size=2,
+    )
     vllm_outputs = vllm_model.generate_greedy(example_prompts, max_tokens)
     del vllm_model