2noise/ChatTTS · error · ValueError

max_num_batched_tokens ({self.max_num_batched_tokens}) is sm

Error message

max_num_batched_tokens ({self.max_num_batched_tokens}) is smaller than max_model_len ({self.max_model_len}). This effectively limits the maximum sequence length to max_num_batched_tokens and makes vLLM reject longer sequences. Please increase max_num_batched_tokens or decrease max_model_len.

What it means

Error "max_num_batched_tokens ({self.max_num_batched_tokens}) is smaller than max_model_len ({self.max_model_len}). This effectively limits the maximum sequence length to max_num_batched_tokens and makes vLLM reject longer sequences. Please increase max_num_batched_tokens or decrease max_model_len." thrown in 2noise/ChatTTS.

Source

Thrown at ChatTTS/model/velocity/configs.py:409

        max_num_batched_tokens: Optional[int],
        max_num_seqs: int,
        max_model_len: int,
        max_paddings: int,
    ) -> None:
        if max_num_batched_tokens is not None:
            self.max_num_batched_tokens = max_num_batched_tokens
        else:
            # If max_model_len is too short, use 2048 as the default value for
            # higher throughput.
            self.max_num_batched_tokens = max(max_model_len, 2048)
        self.max_num_seqs = max_num_seqs
        self.max_model_len = max_model_len
        self.max_paddings = max_paddings
        self._verify_args()

    def _verify_args(self) -> None:
        if self.max_num_batched_tokens < self.max_model_len:
            raise ValueError(
                f"max_num_batched_tokens ({self.max_num_batched_tokens}) is "
                f"smaller than max_model_len ({self.max_model_len}). "
                "This effectively limits the maximum sequence length to "
                "max_num_batched_tokens and makes vLLM reject longer "
                "sequences. Please increase max_num_batched_tokens or "
                "decrease max_model_len."
            )
        if self.max_num_batched_tokens < self.max_num_seqs:
            raise ValueError(
                f"max_num_batched_tokens ({self.max_num_batched_tokens}) must "
                "be greater than or equal to max_num_seqs "
                f"({self.max_num_seqs})."
            )


_STR_DTYPE_TO_TORCH_DTYPE = {
    "half": torch.float16,
    "float16": torch.float16,

View on GitHub (pinned to 77b89ee281)

When it happens

Trigger: Thrown at ChatTTS/model/velocity/configs.py:409 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/19b10d708f8352b7. Report an issue: GitHub.