[OpenVINO] Enable GPU support for OpenVINO vLLM backend (#8192)

vllm/envs.py

@@ -35,6 +35,7 @@ if TYPE_CHECKING:
     VLLM_PP_LAYER_PARTITION: Optional[str] = None
     VLLM_CPU_KVCACHE_SPACE: int = 0
     VLLM_CPU_OMP_THREADS_BIND: str = ""
+    VLLM_OPENVINO_DEVICE: str = "CPU"
     VLLM_OPENVINO_KVCACHE_SPACE: int = 0
     VLLM_OPENVINO_CPU_KV_CACHE_PRECISION: Optional[str] = None
     VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS: bool = False
@@ -302,6 +303,11 @@ environment_variables: Dict[str, Callable[[], Any]] = {
     "VLLM_CPU_OMP_THREADS_BIND":
     lambda: os.getenv("VLLM_CPU_OMP_THREADS_BIND", "all"),
 
+    # OpenVINO device selection
+    # default is CPU
+    "VLLM_OPENVINO_DEVICE":
+    lambda: os.getenv("VLLM_OPENVINO_DEVICE", "CPU").upper(),
+
     # OpenVINO key-value cache space
     # default is 4GB
     "VLLM_OPENVINO_KVCACHE_SPACE":