[Hardware][Intel GPU] Add Intel GPU(XPU) inference backend (#3814)

Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Abhilash Majumder <abhilash.majumder@intel.com>
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
This commit is contained in:
Kunshang Ji
2024-06-17 11:01:25 -07:00
committed by GitHub
co-authored by Jiang Li Abhilash Majumder Abhilash Majumder
parent 1f12122b17
commit 728c4c8a06
31 changed files with 1998 additions and 24 deletions
+2 -2
View File
@@ -3,7 +3,7 @@ from typing import List, Optional, Tuple
from vllm.config import ParallelConfig
from vllm.logger import init_logger
from vllm.utils import get_ip, is_hip
from vllm.utils import get_ip, is_hip, is_xpu
from vllm.worker.worker_base import WorkerWrapperBase
logger = init_logger(__name__)
@@ -71,7 +71,7 @@ def initialize_ray_cluster(
"serving.")
# Connect to a ray cluster.
if is_hip():
if is_hip() or is_xpu():
ray.init(address=ray_address,
ignore_reinit_error=True,
num_gpus=parallel_config.world_size)