vllm.v1.worker.xpu_model_runner ¶

class XPUModelRunner(GPUModelRunner):
    """A model runner for XPU devices."""

    def __init__(
        self,
        vllm_config: VllmConfig,
        device: torch.device,
    ):
        with _torch_cuda_wrapper():
            super().__init__(vllm_config, device)
        # FIXME: To be verified.
        self.cascade_attn_enabled = False

    def _init_device_properties(self) -> None:
        self.num_sms = None

    def _sync_device(self) -> None:
        torch.xpu.synchronize()