diff --git a/tests/e2e/multicard/long_sequence/test_accuracy.py b/tests/e2e/multicard/long_sequence/test_accuracy.py index 7f920c9a..a8bbf50a 100644 --- a/tests/e2e/multicard/long_sequence/test_accuracy.py +++ b/tests/e2e/multicard/long_sequence/test_accuracy.py @@ -81,17 +81,17 @@ def test_output_between_tp_and_cp( } cp_full_kwargs = {} - cp_full_kwargs.update(common_kwargs) - cp_full_kwargs.update(cp_kwargs) + cp_full_kwargs.update(common_kwargs) # type: ignore + cp_full_kwargs.update(cp_kwargs) # type: ignore tp_full_kwargs = {} - tp_full_kwargs.update(common_kwargs) - tp_full_kwargs.update(tp_kwargs) - with VllmRunner(model, **cp_full_kwargs) as runner: + tp_full_kwargs.update(common_kwargs) # type: ignore + tp_full_kwargs.update(tp_kwargs) # type: ignore + with VllmRunner(model, **cp_full_kwargs) as runner: # type: ignore vllm_context_parallel_outputs = runner.generate_greedy( prompts, max_tokens) - with VllmRunner(model, **tp_full_kwargs) as runner: + with VllmRunner(model, **tp_full_kwargs) as runner: # type: ignore vllm_eager_outputs = runner.generate_greedy(prompts, max_tokens) check_outputs_equal(