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

class XPUModelRunnerV2(GPUModelRunnerV2):
    """A model runner for XPU devices."""

    def __init__(
        self,
        vllm_config: VllmConfig,
        device: torch.device,
    ):
        with _torch_cuda_wrapper():
            super().__init__(vllm_config, device)