[Usage]: Resolve: ModuleNotFoundError: No module named 'vllm.model_executor.parallel_utils'

[osafaimal]

[Usage]: Resolve: ModuleNotFoundError: No module named 'vllm.model_executor.parallel_utils'

[osafaimal]

sorry it s not a vllm problem it's a llamaindex problem. can you tell me how i can do the same so i can open a PR or someone else. in all case i will open an issue on their repo.

.venv/lib/python3.11/site-packages/llama_index/llms/vllm/base.py

def __del__(self) -> None:
        import torch

        if torch.cuda.is_available():
            from vllm.model_executor.parallel_utils.parallel_state import (
                destroy_model_parallel,
            )

            destroy_model_parallel()
            del self._client
            torch.cuda.synchronize()

[youkaichao]

vllm.model_executor.parallel_utils.parallel_state is moved to vllm.distributed.parallel_state