[ROCm][CI] Set TORCH_NCCL_BLOCKING_WAIT Distributed Tests On ROCm (#31259)

Signed-off-by: Micah Williamson <micah.williamson@amd.com>

.buildkite/test-amd.yaml

@@ -222,6 +222,9 @@ steps:
   - tests/v1/engine/test_engine_core_client.py
   - tests/distributed/test_symm_mem_allreduce.py
   commands:
+  # Work around HIP bug tracked here: https://github.com/ROCm/hip/issues/3876
+  # TODO: Remove when the bug is fixed in a future ROCm release
+  - export TORCH_NCCL_BLOCKING_WAIT=1
   # test with torchrun tp=2 and external_dp=2
   - torchrun --nproc-per-node=4 distributed/test_torchrun_example.py
   # test with torchrun tp=2 and pp=2
@@ -270,9 +273,10 @@ steps:
   - vllm/v1/executor/uniproc_executor.py
   - vllm/v1/worker/gpu_worker.py
   commands:
-  # https://github.com/NVIDIA/nccl/issues/1838
-  #- export NCCL_CUMEM_HOST_ENABLE=0
   # test with torchrun tp=2 and dp=4 with ep
+  # Work around HIP bug tracked here: https://github.com/ROCm/hip/issues/3876
+  # TODO: Remove when the bug is fixed in a future ROCm release
+  - export TORCH_NCCL_BLOCKING_WAIT=1
   - torchrun --nproc-per-node=8 ../examples/offline_inference/torchrun_dp_example.py --tp-size=2 --pp-size=1 --dp-size=4 --enable-ep
 
 - label: EPLB Algorithm Test # 5min
@@ -1294,6 +1298,9 @@ steps:
   - tests/v1/shutdown
   - tests/v1/worker/test_worker_memory_snapshot.py
   commands:
+  # Work around HIP bug tracked here: https://github.com/ROCm/hip/issues/3876
+  # TODO: Remove when the bug is fixed in a future ROCm release
+  - export TORCH_NCCL_BLOCKING_WAIT=1
   - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
   - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
   - TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py