[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>

setup.py

@@ -233,6 +233,10 @@ def _is_cpu() -> bool:
     return VLLM_TARGET_DEVICE == "cpu"
 
 
+def _is_xpu() -> bool:
+    return VLLM_TARGET_DEVICE == "xpu"
+
+
 def _build_custom_ops() -> bool:
     return _is_cuda() or _is_hip() or _is_cpu()
 
@@ -337,6 +341,8 @@ def get_vllm_version() -> str:
         version += "+tpu"
     elif _is_cpu():
         version += "+cpu"
+    elif _is_xpu():
+        version += "+xpu"
     else:
         raise RuntimeError("Unknown runtime environment")
 
@@ -386,6 +392,8 @@ def get_requirements() -> List[str]:
         requirements = _read_requirements("requirements-tpu.txt")
     elif _is_cpu():
         requirements = _read_requirements("requirements-cpu.txt")
+    elif _is_xpu():
+        requirements = _read_requirements("requirements-xpu.txt")
     else:
         raise ValueError(
             "Unsupported platform, please use CUDA, ROCm, Neuron, or CPU.")