2noise/ChatTTS · error · NotImplementedError

Pipeline parallelism is not supported yet.

Error message

Pipeline parallelism is not supported yet.

What it means

Error "Pipeline parallelism is not supported yet." thrown in 2noise/ChatTTS.

Source

Thrown at ChatTTS/model/velocity/configs.py:373

        self,
        pipeline_parallel_size: int,
        tensor_parallel_size: int,
        worker_use_ray: bool,
        max_parallel_loading_workers: Optional[int] = None,
    ) -> None:
        self.pipeline_parallel_size = pipeline_parallel_size
        self.tensor_parallel_size = tensor_parallel_size
        self.worker_use_ray = worker_use_ray
        self.max_parallel_loading_workers = max_parallel_loading_workers

        self.world_size = pipeline_parallel_size * tensor_parallel_size
        if self.world_size > 1:
            self.worker_use_ray = True
        self._verify_args()

    def _verify_args(self) -> None:
        if self.pipeline_parallel_size > 1:
            raise NotImplementedError("Pipeline parallelism is not supported yet.")


class SchedulerConfig:
    """Scheduler configuration.

    Args:
        max_num_batched_tokens: Maximum number of tokens to be processed in
            a single iteration.
        max_num_seqs: Maximum number of sequences to be processed in a single
            iteration.
        max_model_len: Maximum length of a sequence (including prompt
            and generated text).
        max_paddings: Maximum number of paddings to be added to a batch.
    """

    def __init__(
        self,
        max_num_batched_tokens: Optional[int],

View on GitHub (pinned to 77b89ee281)

When it happens

Trigger: Thrown at ChatTTS/model/velocity/configs.py:373 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of 2noise/ChatTTS@77b89ee281 (2026-08-26). Data as JSON: /api/errors/052ca71f93c5e6dd. Report an issue: GitHub.