2noise/ChatTTS · error · ValueError

load format '{load_format}' is not supported in ROCm. Suppor

Error message

load format '{load_format}' is not supported in ROCm. Supported load format are {rocm_supported_load_format}

What it means

Error "load format '{load_format}' is not supported in ROCm. Supported load format are {rocm_supported_load_format}" thrown in 2noise/ChatTTS.

Source

Thrown at ChatTTS/model/velocity/configs.py:135

        self._verify_quantization()
        self._verify_cuda_graph()

    def _verify_load_format(self) -> None:
        load_format = self.load_format.lower()
        supported_load_format = ["auto", "pt", "safetensors", "npcache", "dummy"]
        rocm_not_supported_load_format = []
        if load_format not in supported_load_format:
            raise ValueError(
                f"Unknown load format: {self.load_format}. Must be one of "
                "'auto', 'pt', 'safetensors', 'npcache', or 'dummy'."
            )
        if is_hip() and load_format in rocm_not_supported_load_format:
            rocm_supported_load_format = [
                f
                for f in supported_load_format
                if (f not in rocm_not_supported_load_format)
            ]
            raise ValueError(
                f"load format '{load_format}' is not supported in ROCm. "
                f"Supported load format are "
                f"{rocm_supported_load_format}"
            )

        # TODO: Remove this check once HF updates the pt weights of Mixtral.
        architectures = getattr(self.hf_config, "architectures", [])
        if "MixtralForCausalLM" in architectures and load_format == "pt":
            raise ValueError(
                "Currently, the 'pt' format is not supported for Mixtral. "
                "Please use the 'safetensors' format instead. "
            )
        self.load_format = load_format

    def _verify_tokenizer_mode(self) -> None:
        tokenizer_mode = self.tokenizer_mode.lower()
        if tokenizer_mode not in ["auto", "slow"]:
            raise ValueError(

View on GitHub (pinned to 77b89ee281)

When it happens

Trigger: Thrown at ChatTTS/model/velocity/configs.py:135 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/530b682b1933a439. Report an issue: GitHub.