vllm.config.kernel ¶

@config
class KernelConfig:
    """Configuration for kernel selection and warmup behavior."""

    enable_flashinfer_autotune: bool = Field(default=None)
    """If True, run FlashInfer autotuning during kernel warmup."""

    def compute_hash(self) -> str:
        """
        WARNING: Whenever a new field is added to this config,
        ensure that it is included in the factors list if
        it affects the computation graph.

        Provide a hash that uniquely identifies all the configs
        that affect the structure of the computation
        graph from input ids/embeddings to the final hidden states,
        excluding anything before input ids/embeddings and after
        the final hidden states.
        """
        # no factors to consider.
        # this config will not affect the computation graph.
        factors: list[Any] = []
        hash_str = safe_hash(str(factors).encode(), usedforsecurity=False).hexdigest()
        return hash_str

    @field_validator("enable_flashinfer_autotune", mode="wrap")
    @classmethod
    def _skip_none_validation(cls, value: Any, handler: Callable) -> Any:
        """Skip validation if the value is `None` when initialization is delayed."""
        if value is None:
            return value
        return handler(value)