def gaudi_awq_config_post_init()

in optimum/habana/transformers/integrations/awq.py [0:0]

• 41 lines of code
• 13 McCabe index (conditional complexity)

def gaudi_awq_config_post_init(self):
    """
    Adapted from: https://github.com/huggingface/transformers/blob/v4.45.2/src/transformers/utils/quantization_config.py#L818
    - support HPU.
    """
    if self.backend not in [AwqBackendPackingMethod.AUTOAWQ]:
        raise ValueError(
            f"Only supported quantization backends in {AwqBackendPackingMethod.AUTOAWQ} - not recognized backend {self.backend}"
        )

    self.version = GaudiAWQLinearVersion.from_str(self.version)
    if self.version not in [
        GaudiAWQLinearVersion.HPU,
        GaudiAWQLinearVersion.GEMM,
    ]:
        raise ValueError(
            f"Only supported versions are in [GaudiAWQLinearVersion.HPU, GaudiAWQLinearVersion.GEMM] - not recognized version {self.version}"
        )

    if self.do_fuse and self.fuse_max_seq_len is None:
        raise ValueError(
            "You cannot enable fused modules without specifying a `fuse_max_seq_len`, make sure to pass a valid `fuse_max_seq_len` for your usecase"
        )

    if self.do_fuse:
        awq_version_supports_fusing = False
        MIN_AWQ_VERSION = "0.1.7"
        if is_auto_awq_available():
            awq_version_supports_fusing = version.parse(importlib.metadata.version("autoawq")) >= version.parse(
                MIN_AWQ_VERSION
            )

        if not awq_version_supports_fusing:
            raise ValueError(
                f"You current version of `autoawq` does not support module fusing, please upgrade `autoawq` package to at least {MIN_AWQ_VERSION}."
            )

    if self.modules_to_not_convert is not None:
        awq_version_supports_non_conversion = False
        MIN_AWQ_VERSION = "0.1.8"
        if is_auto_awq_available():
            awq_version_supports_non_conversion = version.parse(
                importlib.metadata.version("autoawq")
            ) >= version.parse(MIN_AWQ_VERSION)

        if not awq_version_supports_non_conversion:
            raise ValueError(
                f"You current version of `autoawq` does not support module quantization skipping, please upgrade `autoawq` package to at least {MIN_AWQ_VERSION}."
            )

    if self.do_fuse and self.modules_to_fuse is not None:
        raise ValueError("You current implementation of `autoawq` does not support do_fuse and modules_to_fuse.")