[Hardware][TPU] Initial support of model parallelism with single worker using SPMD (#18011)

Signed-off-by: Siyuan Liu <lsiyuan@google.com>
Co-authored-by: Hossein Sarshar <hossein.sarshar@gmail.com>
Co-authored-by: Chengji Yao <chengjiyao@google.com>

vllm/config.py

@@ -1901,6 +1901,8 @@ class ParallelConfig:
             if current_platform.is_neuron():
                 # neuron uses single process to control multiple devices
                 backend = "uni"
+            elif current_platform.is_tpu() and envs.VLLM_XLA_USE_SPMD:
+                backend = "uni"
             elif (current_platform.is_cuda()
                   and cuda_device_count_stateless() < self.world_size):
                 if not ray_found: