mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-04-22 05:37:03 +08:00
a3e4e85ece
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com> Co-authored-by: zhenwei-intel <zhenweiliu@habana.ai>
34 lines
796 B
Python
34 lines
796 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
from typing import TYPE_CHECKING
|
|
|
|
import torch
|
|
|
|
from vllm.config import VllmConfig
|
|
from vllm.logger import init_logger
|
|
from vllm.v1.worker.gpu_model_runner import GPUModelRunner
|
|
|
|
if TYPE_CHECKING:
|
|
pass
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
|
|
class XPUModelRunner(GPUModelRunner):
|
|
"""A model runner for XPU devices."""
|
|
|
|
def __init__(
|
|
self,
|
|
vllm_config: VllmConfig,
|
|
device: torch.device,
|
|
):
|
|
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()
|