Deepseek-v3 Batch Invariant on 8xH100 (#26609)

Signed-off-by: Bram Wasti <bwasti@meta.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

vllm/v1/worker/gpu_worker.py

@@ -764,6 +764,9 @@ def init_worker_distributed_environment(
 ) -> None:
     """Initialize the distributed environment."""
     parallel_config = vllm_config.parallel_config
+    from vllm.model_executor.layers.batch_invariant import init_batch_invariance
+
+    init_batch_invariance()
     set_custom_all_reduce(not parallel_config.disable_custom_all_reduce)
 
     init_distributed_environment(